© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226649
    Prev
    Next
    INDEX
    Explanations

    person does

    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_6_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
    \
    1.34
    {
    1.30
    t
    1.04
    <
    0.97
    Г
    0.83
    V
    0.83
    !
    0.82
        
    0.82
    [
    0.81
    J
    0.78
    POSITIVE LOGITS
    ний
    0.88
    as
    0.74
    ча
    0.71
    ния
    0.68
    ਾ
    0.66
    ων
    0.65
     तत्
    0.64
    perhaps
    0.64
    ти
    0.63
    asile
    0.63
    Activations Density 0.002%

    No Known Activations