© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109282
    Prev
    Next
    INDEX
    Explanations

    google image searches

    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_1_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
    1.21
    ot
    1.07
    ol
    0.98
    는
    0.95
    pero
    0.91
     I
    0.89
     الع
    0.87
    ag
    0.82
     У
    0.81
    h
    0.81
    POSITIVE LOGITS
    न
    1.65
    ل
    1.63
    ন
    1.56
    ن
    1.49
     it
    1.41
    د
    1.40
    ס
    1.38
    น
    1.37
    ่
    1.32
    ン
    1.27
    Activations Density 0.000%

    No Known Activations