© 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. 91949
    Prev
    Next
    INDEX
    Explanations

    levity | us

    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
    ري
    0.72
    s
    0.72
    ן
    0.72
    \
    0.64
     сам
    0.63
    lo
    0.61
     felled
    0.61
    _
    0.61
    ς
    0.61
    ের
    0.59
    POSITIVE LOGITS
    an
    0.99
    S
    0.74
    ků
    0.73
    ↵
    0.69
    માં
    0.69
    ków
    0.66
    ar
    0.65
    quele
    0.65
    aura
    0.65
    dı
    0.64
    Activations Density 0.000%

    No Known Activations