© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107079
    Prev
    Next
    INDEX
    Explanations

    isn't

    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_2_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
     and
    1.13
    ре
    1.13
    ce
    1.09
    리
    1.07
    いう
    1.01
     و
    0.99
    ل
    0.97
    era
    0.92
    led
    0.91
    h
    0.90
    POSITIVE LOGITS
    .
    1.46
    та
    1.40
    ا
    1.26
    ா
    1.17
    ا۔
    1.14
    の頃
    1.09
    的过程中
    1.08
    ের
    1.05
    ها
    1.05
    માં
    1.05
    Activations Density 0.003%

    No Known Activations