© 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. 13550
    Prev
    Next
    INDEX
    Explanations

    a wide variety of mathematical symbols, articles, prepositions, and punctuation within both mathematical notation and general language.

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

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

    punctuation

    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
     myſelf
    -1.94
     itſelf
    -1.84
    ſelves
    -1.82
    ſelf
    -1.81
     ་་
    -1.80
     raiſ
    -1.77
     ―――――
    -1.76
    "]);
    -1.72
    ".
    -1.71
     Jefus
    -1.70
    POSITIVE LOGITS
    ,
    1.41
    .
    1.30
    ?
    1.07
    ;
    1.06
    !
    1.05
     (
    1.02
    :
    1.00
     -
    0.99
     –
    0.95
    (
    0.93
    Activations Density 17.010%

    No Known Activations