© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46951
    Prev
    Next
    INDEX
    Explanations

    FOR counter, 1.FOR loop.revoked its offerthermal fluidspassivation

    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_13_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
     do
    0.15
    at
    0.14
    ad
    0.13
    ান
    0.13
    ك
    0.13
    ungeon
    0.13
    डी
    0.13
    bley
    0.12
    employment
    0.12
    ene
    0.12
    POSITIVE LOGITS
     цвет
    0.16
     پ
    0.16
     sabbam
    0.16
     такая
    0.15
     начинает
    0.15
     первые
    0.15
    是为了
    0.15
     passivation
    0.15
     longitud
    0.15
    вары
    0.15
    Activations Density 0.003%

    No Known Activations