© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9046
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seder
    0.68
     云
    0.67
    ILabel
    0.67
     ৮
    0.65
     sector
    0.64
     misdemean
    0.62
    បន្ទ
    0.62
     empresas
    0.60
    ▌
    0.60
     Terbaru
    0.59
    POSITIVE LOGITS
    GroupLayout
    0.84
     Gav
    0.82
     lui
    0.70
     ஆயிரம்
    0.69
    lui
    0.69
     خص
    0.68
     ಸಾವಿರ
    0.67
     घिरा
    0.66
    Gav
    0.64
    UTS
    0.64
    Activations Density 0.001%

    No Known Activations