© 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. 48340
    Prev
    Next
    INDEX
    Explanations

    smaller, with a long

    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
    Not in Any Lists

    No Comments

    Negative Logits
     мъ
    0.33
    ♂
    0.32
     мужчины
    0.32
     mâles
    0.31
     males
    0.30
     alleys
    0.29
     fachada
    0.29
    Male
    0.29
     honored
    0.29
     thrill
    0.28
    POSITIVE LOGITS
     triv
    0.29
    盂
    0.29
    播出
    0.29
    როს
    0.29
    Disponible
    0.28
    ைய
    0.27
     reminded
    0.27
    Squirrel
    0.27
     torso
    0.27
     দুই
    0.27
    Activations Density 0.029%

    No Known Activations