© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200218
    Prev
    Next
    INDEX
    Explanations

    academic courses

    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_6_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
    g
    1.38
    f
    1.19
    c
    1.10
    gives
    1.02
    gling
    0.99
    gies
    0.98
    ig
    0.98
    gående
    0.94
    gäng
    0.93
    ed
    0.93
    POSITIVE LOGITS
    ς
    1.03
    ل
    1.02
     cocina
    0.97
     voda
    0.94
    ו
    0.92
     negocios
    0.91
     shrine
    0.91
     Fonbet
    0.90
     UBND
    0.88
     courthouse
    0.88
    Activations Density 0.002%

    No Known Activations