© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206471
    Prev
    Next
    INDEX
    Explanations

    sequential data

    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_37_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
    igkeit
    0.44
    ᑦ
    0.42
    луч
    0.39
    Emit
    0.39
    cą
    0.39
    ｮ
    0.39
    вость
    0.38
     ভোক
    0.38
    unzione
    0.38
    𝗁
    0.38
    POSITIVE LOGITS
    值得
    0.38
    ometrically
    0.37
     descended
    0.37
     Manning
    0.37
     Commercial
    0.36
    ials
    0.35
     Mana
    0.35
     commercial
    0.34
     claiming
    0.34
     organ
    0.34
    Activations Density 0.001%

    No Known Activations