© 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. 19135
    Prev
    Next
    INDEX
    Explanations

    box geometry

    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
    Phe
    0.41
    domains
    0.38
     Helv
    0.38
    validators
    0.37
     Schwartz
    0.36
     Passive
    0.36
    莗
    0.35
     Phe
    0.35
    Salon
    0.35
     recapit
    0.35
    POSITIVE LOGITS
    োপাধ
    0.41
    ㄝ
    0.38
     axes
    0.38
     allocator
    0.38
    Bracket
    0.37
     sè
    0.37
     creatine
    0.36
    )';
    0.36
     getc
    0.36
     ক্যাম্পে
    0.36
    Activations Density 0.001%

    No Known Activations