© 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. 40873
    Prev
    Next
    INDEX
    Explanations

    voice-over script

    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
    ↵
    0.91
    و
    0.86
    <0x0D>
    0.77
    ু
    0.68
    ו
    0.68
    0.63
    다
    0.61
    ्स
    0.61
    <0xE3>
    0.61
    ริ
    0.60
    POSITIVE LOGITS
     for
    1.02
     at
    0.95
    ’
    0.94
     an
    0.84
     on
    0.81
     by
    0.76
     the
    0.74
     its
    0.70
     from
    0.69
     współ
    0.68
    Activations Density 0.006%

    No Known Activations