© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260966
    Prev
    Next
    INDEX
    Explanations

    binary search result not -1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    Mitsubishi
    0.84
    ا
    0.79
    та
    0.76
     Mitsubishi
    0.75
    Ability
    0.74
    AA
    0.73
    orit
    0.72
    abilities
    0.72
    boost
    0.72
     LIMITED
    0.71
    POSITIVE LOGITS
     portavoz
    0.93
     sark
    0.88
     للخ
    0.82
     decorar
    0.79
     spokesperson
    0.78
     teinture
    0.78
     次
    0.77
     inflación
    0.77
     dersimizde
    0.76
     noon
    0.76
    Activations Density 0.001%

    No Known Activations