© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194180
    Prev
    Next
    INDEX
    Explanations

    this thing

    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_4_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
    в
    1.35
    ية
    1.16
    к
    1.13
    í
    1.05
     It
    1.04
    Ε
    1.01
    It
    0.99
    з
    0.93
     you
    0.89
    ב
    0.89
    POSITIVE LOGITS
    and
    1.42
    tries
    0.99
    กฎ
    0.94
    ight
    0.91
    ↵↵
    0.87
    tellers
    0.82
    是什麼
    0.82
    int
    0.78
    $('#
    0.77
     відпо
    0.77
    Activations Density 0.002%

    No Known Activations