© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42152
    Prev
    Next
    INDEX
    Explanations

    Young, Kirishima, Kyrgyzstan

    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
    و
    0.97
    o
    0.88
    a
    0.82
    in
    0.76
    ك
    0.72
    다
    0.70
    and
    0.68
    is
    0.67
    k
    0.66
    am
    0.66
    POSITIVE LOGITS
     pravil
    0.63
     perdu
    0.61
     squre
    0.59
     hairy
    0.57
     hautes
    0.57
    પ
    0.57
    ט
    0.56
    ഹന
    0.56
    富士
    0.54
     Subram
    0.54
    Activations Density 0.000%

    No Known Activations