© 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. 121691
    Prev
    Next
    INDEX
    Explanations

    high

    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
    Negative Logits
     (
    0.74
     o
    0.68
     e
    0.67
     EEOC
    0.64
     ร
    0.62
     ว
    0.61
    면
    0.61
     temer
    0.61
    ing
    0.60
     pointing
    0.60
    POSITIVE LOGITS
    ’
    0.87
    _
    0.84
    ارة
    0.72
    '
    0.70
    ро
    0.66
    aturas
    0.64
    ко
    0.61
    \$
    0.61
    _=
    0.60
    ని
    0.60
    Activations Density 0.003%

    No Known Activations