© 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. 10372
    Prev
    Next
    INDEX
    Explanations

    logging format timestamp

    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
    LabelTool
    0.37
    Grouping
    0.37
    παϊ
    0.37
     factorización
    0.37
    Фі
    0.37
     shadowing
    0.36
    hnen
    0.36
     morphological
    0.36
    ваць
    0.36
    ള
    0.36
    POSITIVE LOGITS
     Create
    0.38
    writeToFile
    0.37
     O
    0.37
     Naturally
    0.37
     Inher
    0.36
    CreateIndex
    0.36
     Ar
    0.35
    Info
    0.35
     sang
    0.35
     CREATE
    0.35
    Activations Density 0.002%

    No Known Activations