© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14323
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that end sentences or clauses

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

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

    Punctuation

    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
     the
    -0.68
    .
    -0.64
     
    -0.64
     I
    -0.62
     to
    -0.59
    ...
    -0.59
     G
    -0.58
     in
    -0.58
     L
    -0.57
     a
    -0.57
    POSITIVE LOGITS
     виправивши
    1.51
     مرئيه
    1.40
     متعلقه
    1.40
    rungsseite
    1.33
    InjectAttribute
    1.23
     Мексичка
    1.23
     فريبيس
    1.20
     GenerationType
    1.19
    parsedMessage
    1.17
    TagMode
    1.16
    Activations Density 2.735%

    No Known Activations