© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 374
    Prev
    Next
    INDEX
    Explanations

    javascript code syntax including parentheses, curly braces, functions, and object properties

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    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
     betweenstory
    -0.91
    expandindo
    -0.76
     وتسجيلات
    -0.66
    PointSize
    -0.64
    gridy
    -0.60
    ligibility
    -0.59
     كومونز
    -0.59
     referenties
    -0.57
    orari
    -0.57
     linearized
    -0.56
    POSITIVE LOGITS
    (':
    0.78
    ngdoc
    0.71
     ':
    0.69
    [`
    0.66
     $[-
    0.59
     //$
    0.57
     {:.
    0.57
    ($__
    0.56
     =$
    0.56
    =`
    0.55
    Activations Density 2.858%

    No Known Activations