© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229340
    Prev
    Next
    INDEX
    Explanations

    opposite

    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_6_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
    '
    1.73
    在
    1.59
    (
    1.30
    も
    1.29
     in
    1.27
    도
    1.23
     שה
    1.09
     motel
    1.08
    もら
    1.05
    在哪里
    1.01
    POSITIVE LOGITS
    V
    1.01
    as
    0.98
    s
    0.95
    N
    0.92
    />
    0.90
    ly
    0.87
    ى
    0.87
    sol
    0.85
    sky
    0.84
    ాప
    0.84
    Activations Density 0.001%

    No Known Activations