© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10595
    Prev
    Next
    INDEX
    Explanations

    code snippets that includes certain numbers

    oai_token-act-pair · gemini-2.0-flash

    5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     resourceCulture
    -0.97
    PreferredItem
    -0.78
     ModelExpression
    -0.78
    новниш
    -0.70
     jsPsych
    -0.69
     nahilalakip
    -0.69
    BindingResult
    -0.69
     Reverso
    -0.67
    MigrationBuilder
    -0.67
     gynhyrchwyd
    -0.67
    POSITIVE LOGITS
    5
    0.49
    4
    0.47
    ‭
    0.46
     ne
    0.46
    mar
    0.43
     Ne
    0.43
     mar
    0.43
     بيها
    0.42
    se
    0.40
    MOD
    0.40
    Activations Density 1.183%

    No Known Activations