© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201072
    Prev
    Next
    INDEX
    Explanations

    American football teams

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     G
    0.45
    unta
    0.41
    ంచు
    0.40
    рма
    0.38
     Mam
    0.37
    కర
    0.37
     Carrier
    0.37
    Am
    0.37
     Denn
    0.37
    Unt
    0.36
    POSITIVE LOGITS
    Greg
    0.55
     Greg
    0.53
     greg
    0.49
    cumsum
    0.41
     }*/
    0.40
    كد
    0.40
    됩
    0.40
    @]
    0.40
    koľ
    0.40
    Steven
    0.39
    Activations Density 0.000%

    No Known Activations