© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74490
    Prev
    Next
    INDEX
    Explanations

    at a specific time or location

    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_31_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
    abases
    0.40
    Bold
    0.40
    マンション
    0.39
     मलिक
    0.38
    マリン
    0.38
    IllegalArgument
    0.38
    㗎
    0.37
    italic
    0.36
    マリ
    0.36
     Milli
    0.35
    POSITIVE LOGITS
     interface
    0.38
    oruč
    0.37
     تر
    0.35
     trä
    0.35
     Permit
    0.34
    നെ
    0.34
     trance
    0.34
    äk
    0.33
    !("{}",
    0.33
    㒵
    0.33
    Activations Density 0.000%

    No Known Activations