© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10573
    Prev
    Next
    INDEX
    Explanations

    programming code snippets, including function definitions, error handling, variable declarations, and API calls.

    oai_token-act-pair · gemini-2.0-flash

    code or configuration snippets

    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
    prehensive
    -0.97
    ratulations
    -0.92
    ouncil
    -0.86
    æus
    -0.84
    ecutive
    -0.84
    unisex
    -0.82
    ficulty
    -0.82
    nicity
    -0.82
    NEYS
    -0.80
     v
    -0.79
    POSITIVE LOGITS
     Reſ
    0.73
     Diſ
    0.73
     Plin
    0.72
     Anſ
    0.71
     Offisielt
    0.71
     Sext
    0.71
     Epist
    0.70
    One
    0.70
     Toen
    0.67
     ovp
    0.67
    Activations Density 5.527%

    No Known Activations