© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198096
    Prev
    Next
    INDEX
    Explanations

    vulnerability scoring system CVSS

    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_12_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
    '
    0.66
    ব
    0.55
    q
    0.55
    "
    0.54
    レース
    0.50
     любые
    0.50
    };
    0.49
    Rails
    0.48
    バス
    0.48
    ו
    0.48
    POSITIVE LOGITS
     և
    0.61
    steins
    0.56
    ﻴ
    0.56
    iping
    0.54
    ImageBeforeText
    0.54
    liche
    0.53
    یمی
    0.50
     साढ़े
    0.49
     și
    0.48
    țiuni
    0.48
    Activations Density 0.005%

    No Known Activations