© 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. 241253
    Prev
    Next
    INDEX
    Explanations

    email/password authentication

    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
     retarded
    0.38
     Canton
    0.38
     Unwin
    0.37
     retard
    0.37
    бив
    0.37
     Retreat
    0.36
    スタイ
    0.36
     жела
    0.36
    στα
    0.36
    객
    0.35
    POSITIVE LOGITS
    িনী
    0.43
    altet
    0.38
     latar
    0.37
    esus
    0.37
    isture
    0.37
     contentView
    0.37
    dometer
    0.37
    Tra
    0.36
    ီ
    0.36
     আকাশ
    0.36
    Activations Density 0.000%

    No Known Activations