© 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. 3009
    Prev
    Next
    INDEX
    Explanations

    statements about research results and insights

    oai_token-act-pair · gemini-2.0-flash

    articles and qualitative insights

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

    provide

    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
     يتيمه
    -0.76
    SourceChecksum
    -0.65
     ComVisible
    -0.64
     ModelExpression
    -0.62
     disambiguazione
    -0.59
    ThemeOverlay
    -0.59
    HasForeignKey
    -0.58
    addCriterion
    -0.58
    EnableWeb
    -0.58
    EndGlobalSection
    -0.57
    POSITIVE LOGITS
     ſome
    0.61
     ſeveral
    0.59
     some
    0.56
     guidelines
    0.56
     a
    0.56
     an
    0.56
     documentary
    0.55
     myſelf
    0.55
     interpretation
    0.54
     houſe
    0.53
    Activations Density 4.569%

    No Known Activations