© 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. 7751
    Prev
    Next
    INDEX
    Explanations

    language related to political issues involving healthcare and legislation

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 're'

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

    policy proposals

    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
    AtIndexPath
    -0.48
    انجليز
    -0.45
    <?>
    -0.44
    onFailure
    -0.44
     arras
    -0.43
     artikkeli
    -0.43
     purpure
    -0.42
    isLoaded
    -0.42
    fprintf
    -0.42
    GroupLayout
    -0.42
    POSITIVE LOGITS
    Personendaten
    0.66
     Repe
    0.66
     bì
    0.64
     Naam
    0.64
     ending
    0.63
    repe
    0.63
     reparations
    0.61
     Repar
    0.61
     Measures
    0.60
    addContainerGap
    0.60
    Activations Density 3.215%

    No Known Activations