© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193886
    Prev
    Next
    INDEX
    Explanations

    right whales, branding, breeding, site

    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_15_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
    f
    0.57
    ش
    0.54
     nond
    0.53
     feel
    0.52
     beetles
    0.50
     infer
    0.50
     espe
    0.49
    开始
    0.49
     jac
    0.48
    フ
    0.48
    POSITIVE LOGITS
    IDField
    0.54
    ID
    0.53
    ORE
    0.53
     พิจิก
    0.53
    HY
    0.52
    illi
    0.50
    ITURE
    0.50
    脲
    0.49
    ಧ್ಯ
    0.48
     സ്ഥല
    0.48
    Activations Density 0.000%

    No Known Activations