© 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. 10705
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs coupled with words that indicate positive sentiment

    oai_token-act-pair · gemini-2.0-flash

    unique nouns or titles

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

    reviews/descriptions

    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
    ISupport
    -0.90
     doPost
    -0.79
    WireFormatLite
    -0.68
    saraba
    -0.61
     Rien
    -0.60
     Tym
    -0.59
    "}";
    -0.59
     Commencez
    -0.59
     Compose
    -0.59
    BASEPATH
    -0.58
    POSITIVE LOGITS
    Portail
    0.52
    Aholisi
    0.50
    Portale
    0.49
    estacks
    0.49
    ménage
    0.46
    ayne
    0.46
    GEBURTSDATUM
    0.42
     přek
    0.41
    StreetMap
    0.41
    ↘
    0.40
    Activations Density 1.599%

    No Known Activations