© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7911
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate a problem or warning, or alternatives.

    oai_token-act-pair · gemini-2.0-flash

    say or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     or
    -3.27
     или
    -2.42
    或
    -2.22
     atau
    -2.08
     eller
    -1.98
    或者
    -1.95
     یا
    -1.93
     oder
    -1.92
    หรือ
    -1.92
     nebo
    -1.91
    POSITIVE LOGITS
     mxArray
    0.77
    usermodel
    0.66
    principalTable
    0.63
     lenker
    0.57
    談社
    0.57
    ⓧ
    0.57
    "],
    0.56
    +};
    0.56
    MessageOf
    0.55
    inaison
    0.54
    Activations Density 2.261%

    No Known Activations