© 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. 7061
    Prev
    Next
    INDEX
    Explanations

    sentences that refer to narrative or plot points in films, television shows, or books

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "leading"

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

    related to stories

    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
     CURIAM
    -0.63
    addGap
    -0.56
    lichung
    -0.52
    TabLayout
    -0.51
    aronder
    -0.50
     Censo
    -0.48
    twimg
    -0.47
    JsonPropertyName
    -0.46
     Vikipedi
    -0.45
    ophthal
    -0.45
    POSITIVE LOGITS
     leading
    0.78
    leading
    0.71
    Leading
    0.69
     Leading
    0.66
    CopyWith
    0.62
    adpleegd
    0.60
     cul
    0.59
    LEADING
    0.57
    PropertyGroup
    0.56
    าสตร์
    0.55
    Activations Density 4.034%

    No Known Activations