© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62563
    Prev
    Next
    INDEX
    Explanations

    exclamation and claim

    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_11_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
    AP
    0.77
    AB
    0.73
    OP
    0.71
    OU
    0.70
    SA
    0.67
    He
    0.66
    O
    0.64
    .
    0.64
    At
    0.63
    So
    0.63
    POSITIVE LOGITS
    t
    0.73
     smothered
    0.66
    i
    0.66
    ಗ್ಗೆ
    0.63
    ബരിമല
    0.63
    间的
    0.61
     exile
    0.61
    ுறு
    0.60
    莽
    0.59
    м
    0.59
    Activations Density 0.001%

    No Known Activations