© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142494
    Prev
    Next
    INDEX
    Explanations

    venture capital firms

    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_12_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
    Ꭻ
    0.44
     circulating
    0.42
    АР
    0.41
    ૧
    0.41
     dipping
    0.41
     commuters
    0.41
    题材
    0.41
     हक
    0.40
     а
    0.40
     observers
    0.40
    POSITIVE LOGITS
    Dat
    0.48
    Lab
    0.45
    Str
    0.44
    feito
    0.44
    ClNO
    0.43
    LP
    0.43
    Cit
    0.43
    Manual
    0.43
    Som
    0.42
     ĝi
    0.42
    Activations Density 0.001%

    No Known Activations