© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141669
    Prev
    Next
    INDEX
    Explanations

    prima / primi / primit

    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_0_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
    <0x80>
    1.30
    ্যা
    1.27
    ra
    1.22
    বে
    1.20
    ล
    1.19
    ால்
    1.14
    एर
    1.10
    ۰
    1.09
    おそらく
    1.05
    д
    1.04
    POSITIVE LOGITS
    IN
    1.86
    a
    1.77
    k
    1.71
    1
    1.71
    o
    1.50
    n
    1.47
    ką
    1.42
    kst
    1.42
    P
    1.42
    ться
    1.40
    Activations Density 0.000%

    No Known Activations