© 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. 8991
    Prev
    Next
    INDEX
    Explanations

    varied words that are positive or negative and seem important to the author

    oai_token-act-pair · gemini-2.0-flash

    words related to technical issues or web development

    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
     
    -0.79
    ↵↵
    -0.72
     (
    -0.70
    -0.69
    ;
    -0.68
    <eos>
    -0.68
    }
    -0.66
    (
    -0.66
     the
    -0.64
    x
    -0.63
    POSITIVE LOGITS
    rungsseite
    1.55
     незавершена
    1.48
     متعلقه
    1.39
    MigrationBuilder
    1.38
    IntoConstraints
    1.36
    TagMode
    1.31
     Мексичка
    1.30
    parsedMessage
    1.29
     виправивши
    1.29
    AndEndTag
    1.28
    Activations Density 9.912%
    No Known Activations