© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79729
    Prev
    Next
    INDEX
    Explanations

    kats, chts, tats, ats

    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_0_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
    не
    2.22
    ن
    2.14
    ם
    2.13
    p
    2.00
    y
    2.00
    c
    1.97
    k
    1.90
    n
    1.88
    ন
    1.78
    לי
    1.77
    POSITIVE LOGITS
    :
    1.60
    I
    1.55
    (
    1.41
    ors
    1.28
    Y
    1.19
    AV
    1.16
    Einzelnachweise
    1.16
    .
    1.09
    {
    1.09
    Ob
    1.08
    Activations Density 0.000%

    No Known Activations