© 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. 7411
    Prev
    Next
    INDEX
    Explanations

    words and phrases about legal/financial matters that are the result of some incident happening

    oai_token-act-pair · gemini-2.0-flash

    punctuation and formatting tokens

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

    code/text

    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
     Efq
    -2.23
     Theſe
    -2.09
     myſelf
    -2.06
    parsedMessage
    -2.02
     itſelf
    -2.00
     Monfieur
    -2.00
     Мексичка
    -1.98
    rungsseite
    -1.95
    expandindo
    -1.91
     виправивши
    -1.88
    POSITIVE LOGITS
     
    1.28
    <eos>
    1.09
     (
    1.04
    ↵↵
    1.03
    ,
    1.02
    .
    0.96
    ↵
    0.92
    ;
    0.91
     in
    0.90
     [
    0.85
    Activations Density 10.452%

    No Known Activations