© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6337
    Prev
    Next
    INDEX
    Explanations

    medical studies or advice

    oai_token-act-pair · gemini-2.0-flash

    archaic or old-fashioned terms

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

    Monfieur

    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
     
    -0.79
    .
    -0.78
    ,
    -0.77
    ↵
    -0.72
    ↵↵
    -0.71
    <eos>
    -0.69
     (
    -0.69
    -
    -0.68
     to
    -0.66
     upon
    -0.63
    POSITIVE LOGITS
     Monfieur
    1.33
     myſelf
    1.31
     ainfi
    1.30
     auroit
    1.30
     purpoſe
    1.28
     feroit
    1.27
     avoient
    1.25
     Efq
    1.23
     auffi
    1.23
     Theſe
    1.23
    Activations Density 1.480%

    No Known Activations