© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78267
    Prev
    Next
    INDEX
    Explanations

    patrol the road, waters, car, vessel

    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_0_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
    ુ
    1.53
    ą
    1.44
    ಲ್ಲಿ
    1.26
    ες
    1.25
    কে
    1.23
    ী
    1.16
    큼
    1.14
    étais
    1.13
    ции
    1.12
    ますが
    1.11
    POSITIVE LOGITS
    ك
    2.05
    i
    1.83
    ح
    1.78
     of
    1.70
    S
    1.58
    O
    1.57
    al
    1.44
    P
    1.38
    على
    1.38
    E
    1.36
    Activations Density 0.000%

    No Known Activations