© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78460
    Prev
    Next
    INDEX
    Explanations

    G followed by numbers or punctuation

    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_0_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
     as
    1.32
    ז
    1.31
     (
    1.12
     extraordinaire
    1.10
     çant
    1.10
    ος
    1.09
     econometric
    1.09
     coste
    1.09
     ομά
    1.09
     insuff
    1.07
    POSITIVE LOGITS
    j
    1.36
    i
    1.30
    و
    1.29
    t
    1.26
    )
    1.20
    ان
    1.17
    }
    1.14
    os
    1.13
    in
    1.10
    l
    1.10
    Activations Density 0.002%

    No Known Activations