© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7680
    Prev
    Next
    INDEX
    Explanations

    Montana

    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_39_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
    uin
    0.36
    asty
    0.36
    itaria
    0.35
    "^
    0.35
    uidor
    0.34
     nig
    0.34
    前进
    0.34
    arote
    0.34
    [*
    0.33
    ierge
    0.33
    POSITIVE LOGITS
    Montana
    0.93
     Montana
    0.91
     montana
    0.68
     MONT
    0.63
     Zambia
    0.53
     Yellowstone
    0.50
     Montenegro
    0.48
    MONT
    0.45
     Мон
    0.44
     mont
    0.44
    Activations Density 0.005%

    No Known Activations