© 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. 7272
    Prev
    Next
    INDEX
    Explanations

    months and occasionally ordinal numbers that could be part of a date

    oai_token-act-pair · gemini-2.0-flash

    dates and punctuation

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

    months

    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
    RenderAtEndOf
    -0.82
     Meksiku
    -0.79
    oa̍t
    -0.76
    ſelf
    -0.73
     uſed
    -0.72
    脚注の使い方
    -0.71
     GIPHY
    -0.70
    醐
    -0.70
    EDEFAULT
    -0.68
    wiſe
    -0.67
    POSITIVE LOGITS
    ,
    0.48
     ’
    0.47
    Биография
    0.45
    viewtopic
    0.45
    query
    0.44
     –
    0.43
    onOptions
    0.43
     CURIAM
    0.43
    ioutil
    0.42
     into
    0.42
    Activations Density 0.928%

    No Known Activations