© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24613
    Prev
    Next
    INDEX
    Explanations

    root path (`/`) followed by class or link names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    3
    0.98
    O
    0.91
    ot
    0.91
    س
    0.91
    T
    0.88
    1
    0.87
    C
    0.84
    P
    0.83
    D
    0.83
    8
    0.83
    POSITIVE LOGITS
    ки
    0.91
    ası
    0.77
    ᱐
    0.77
    ている
    0.76
    ری
    0.73
    inės
    0.71
     Russie
    0.71
    ㎖
    0.71
     nomi
    0.70
    toon
    0.70
    Activations Density 0.006%

    No Known Activations