© 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. 12004
    Prev
    Next
    INDEX
    Explanations

    Java code comments, specifically the '@' symbol followed by parameter names, return types or other annotations

    oai_token-act-pair · gemini-2.0-flash

    @

    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
     Pohl
    -0.57
    izzi
    -0.52
    oncesto
    -0.52
     nationaux
    -0.51
    ituaries
    -0.50
    enterian
    -0.50
    pecially
    -0.50
    lafen
    -0.50
    jualan
    -0.50
    athione
    -0.50
    POSITIVE LOGITS
     resourceCulture
    0.89
    ⓧ
    0.78
    elemField
    0.73
    ByExample
    0.67
    WriteBarrier
    0.63
    windowFixed
    0.63
    новниш
    0.61
    UnusedPrivate
    0.60
     onAnimation
    0.60
     ***!
    0.60
    Activations Density 2.906%

    No Known Activations