© 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. 4388
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

    oai_token-act-pair · gemini-2.0-flash

    multi-language references or citations

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

    digits

    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
    ️⃣
    -0.70
    
    -0.63
    ⃣
    -0.61
     salu
    -0.53
    EFIAPI
    -0.53
    tvguidetime
    -0.51
     Meksiku
    -0.51
     westfalen
    -0.50
    COMPAT
    -0.50
     MonoBehaviour
    -0.49
    POSITIVE LOGITS
    Примечания
    0.69
     '{@
    0.68
    Bronnen
    0.62
     unknownFields
    0.59
     colspan
    0.55
    HTH
    0.53
    moveToFirst
    0.53
    Referanser
    0.51
    WebVitals
    0.51
    彿
    0.50
    Activations Density 5.856%

    No Known Activations