© 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. 10677
    Prev
    Next
    INDEX
    Explanations

    a variety of items, including numbers, file extensions, dates, and certain words, without a clear unifying theme.

    oai_token-act-pair · gemini-2.0-flash

    Code/data references

    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
     []).
    -0.54
    .
    -0.50
    //
    -0.49
    。
    -0.42
    //.
    -0.41
    ().
    -0.41
    ற்
    -0.40
     "".
    -0.40
    was
    -0.39
     dictadura
    -0.39
    POSITIVE LOGITS
     للاسماء
    1.16
     للمعارف
    0.85
    invokeLater
    0.83
    OOTDTY
    0.82
    AllAfrica
    0.79
    Referències
    0.79
    ècie
    0.77
    LookAnd
    0.77
    MessageOf
    0.76
    AutoScaleMode
    0.76
    Activations Density 10.813%

    No Known Activations