© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111592
    Prev
    Next
    INDEX
    Explanations

    tonight, tonumber, tonnage, tonkatsu

    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_2_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
    on
    1.95
    ان
    1.81
    ن
    1.68
    ন
    1.64
    н
    1.57
    न
    1.39
    an
    1.35
    un
    1.31
    يل
    1.31
    ला
    1.29
    POSITIVE LOGITS
    s
    1.22
    d
    1.09
     I
    1.07
    '
    1.06
    (
    1.02
    ۰
    1.02
    ς
    0.92
     adduct
    0.90
    wadi
    0.89
    dı
    0.88
    Activations Density 0.001%

    No Known Activations