© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121787
    Prev
    Next
    INDEX
    Explanations

    plant, garden, apple, plug, Lorca, explosion

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    म
    0.73
    بہ
    0.70
    О
    0.68
    بے
    0.66
    Lookup
    0.65
    DEBUG
    0.64
    enic
    0.64
    د
    0.63
    ab
    0.62
    Garden
    0.61
    POSITIVE LOGITS
    ’
    0.78
    '
    0.62
     swam
    0.61
     swim
    0.58
     Swim
    0.58
    ᕗ
    0.56
     I
    0.55
    kannya
    0.55
     RAND
    0.54
    toare
    0.54
    Activations Density 0.007%

    No Known Activations