© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 55062
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    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_55_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
    yyyy
    0.81
    yyyyyyyy
    0.78
    ுள்ளனர்
    0.76
    ுள்ள
    0.73
    yy
    0.67
    ுள்ளார்
    0.63
    ுள்ளது
    0.62
    YY
    0.62
    ়
    0.61
    outube
    0.61
    POSITIVE LOGITS
    speople
    0.58
    pple
    0.49
    ppers
    0.46
    ziert
    0.44
    ppel
    0.44
    swith
    0.43
    icules
    0.42
    ğe
    0.41
    ിൽ
    0.41
    ाम
    0.40
    Activations Density 0.037%

    No Known Activations