© 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. 1246
    Prev
    Next
    INDEX
    Explanations

    phrases or sentence components within news articles or political analyses.

    oai_token-act-pair · gemini-2.0-flash

    commas

    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
     (
    -0.73
    AutoScaleMode
    -0.58
    UrlResolution
    -0.54
    horabuena
    -0.51
    二是
    -0.51
     mẽ
    -0.50
    --(
    -0.49
    ToBounds
    -0.49
    berdayakan
    -0.49
    这就
    -0.49
    POSITIVE LOGITS
    oneofs
    0.55
    Diweddarwch
    0.54
     TextAppearance
    0.52
    bieter
    0.51
    脚注の使い方
    0.50
    ρώ
    0.50
    Nef
    0.49
    <?,
    0.48
     /\.
    0.48
    unhofer
    0.48
    Activations Density 6.011%

    No Known Activations