© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221671
    Prev
    Next
    INDEX
    Explanations

    `.so` shared library files

    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_10_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
     I
    0.64
     e
    0.56
     ı
    0.53
     población
    0.52
     lá
    0.49
     revolutions
    0.49
    %)
    0.48
     not
    0.47
     goo
    0.47
     arbor
    0.47
    POSITIVE LOGITS
    '
    0.59
    к
    0.55
    that
    0.52
    г
    0.51
    де
    0.50
    _
    0.49
    W
    0.48
    ш
    0.47
    van
    0.46
    ש
    0.46
    Activations Density 0.003%

    No Known Activations