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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125010
    Prev
    Next
    INDEX
    Explanations

    Believe it or not

    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_3_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
    ↵
    1.16
     be
    1.11
    '
    1.02
    CT
    0.94
     can
    0.92
     was
    0.91
    ST
    0.88
     for
    0.82
    for
    0.82
    </h3>
    0.78
    POSITIVE LOGITS
    in
    0.94
    t
    0.86
    보
    0.77
    트
    0.76
    적으로
    0.76
    트에
    0.75
    ล
    0.75
    ัง
    0.74
    상
    0.73
    ק
    0.71
    Activations Density 0.000%

    No Known Activations