© 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. 8028
    Prev
    Next
    INDEX
    Explanations

    the word "of" and words related to it, particularly short words around it

    oai_token-act-pair · gemini-2.0-flash

    technical or programming keywords

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

    Code-related tokens

    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
    ­
    -0.50
    cas
    -0.49
    </h2>
    -0.48
     &
    -0.46
     to
    -0.45
    й
    -0.45
    og
    -0.45
    ang
    -0.45
     about
    -0.45
    ink
    -0.44
    POSITIVE LOGITS
    uxxxx
    1.19
    SourceChecksum
    1.00
     ModelExpression
    0.93
     AssemblyCulture
    0.92
    ValueStyle
    0.90
     समीक्षक
    0.89
    ViewImports
    0.85
    RenderAtEndOf
    0.85
    IntoConstraints
    0.85
    CodeAttribute
    0.84
    Activations Density 6.468%

    No Known Activations