© 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. 9291
    Prev
    Next
    INDEX
    Explanations

    youtube

    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
    świę
    0.69
     찾아
    0.68
     رام
    0.67
    ফোন
    0.66
    思議
    0.66
    findById
    0.65
    𝟮
    0.65
     ২০২০
    0.64
     addItem
    0.64
     systeem
    0.64
    POSITIVE LOGITS
    炭
    0.76
    ृता
    0.68
     BURN
    0.67
     بلوچستان
    0.66
    uasion
    0.65
     ke
    0.63
     burn
    0.63
    ほど
    0.62
    udi
    0.62
    upgrade
    0.62
    Activations Density 0.005%

    No Known Activations