© 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. 127846
    Prev
    Next
    INDEX
    Explanations

    GTX, RTX, Llama

    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
    a
    0.77
    aia
    0.73
    is
    0.68
    as
    0.68
    sp
    0.68
    d
    0.66
    call
    0.66
    track
    0.66
    it
    0.65
    h
    0.63
    POSITIVE LOGITS
    ן
    0.77
    ي
    0.68
    ệt
    0.65
     Gu
    0.64
     guarantees
    0.61
     cares
    0.61
    ینگ
    0.61
    મ
    0.60
     of
    0.60
    ENT
    0.60
    Activations Density 0.000%

    No Known Activations