© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19080
    Prev
    Next
    INDEX
    Explanations

    raw string r"..."

    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_40_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
    FILE
    0.44
     қар
    0.40
    LU
    0.39
    Lu
    0.39
     金
    0.38
    Sandbox
    0.38
     Fare
    0.37
    rotechn
    0.37
     பணிய
    0.36
     Sandbox
    0.36
    POSITIVE LOGITS
    fromRGBO
    0.41
     mites
    0.39
    šky
    0.39
    dbh
    0.39
     lak
    0.38
     Nitro
    0.37
    Nitro
    0.37
    󠁣
    0.37
     век
    0.36
    ocrates
    0.36
    Activations Density 0.002%

    No Known Activations