© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4120
    Prev
    Next
    INDEX
    Explanations

    common words like prepositions, articles, conjunctions, and possessives, along with some adjectives and numbers, seemingly acting as a sort of structural element recognizer

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     automatiques
    -0.73
     rapides
    -0.61
     démocr
    -0.60
     réguli
    -0.59
     élas
    -0.58
     positifs
    -0.57
     électriques
    -0.56
     juridiques
    -0.56
     élevés
    -0.55
     électroniques
    -0.53
    POSITIVE LOGITS
     defaultstate
    0.91
    RenderAtEndOf
    0.86
    IMPORTED
    0.82
    UnusedPrivate
    0.79
    ########.
    0.75
     Baillargeon
    0.74
     nakalista
    0.74
     مشين
    0.74
    RegistryLite
    0.73
     referenties
    0.73
    Activations Density 3.114%

    No Known Activations