© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91807
    Prev
    Next
    INDEX
    Explanations

    stereotypical

    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
    \
    0.84
    '
    0.77
    ле
    0.66
     большую
    0.63
     letra
    0.63
    _
    0.61
     besi
    0.61
    plement
    0.59
     последствия
    0.58
     paragra
    0.58
    POSITIVE LOGITS
    с
    0.83
    at
    0.82
    ac
    0.78
    as
    0.76
    el
    0.75
    5
    0.74
    6
    0.74
    یس
    0.74
    س
    0.74
    os
    0.73
    Activations Density 0.000%

    No Known Activations