© 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. 113232
    Prev
    Next
    INDEX
    Explanations

    Orkney

    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
    that
    1.30
    ،
    1.27
    ir
    1.20
    I
    1.20
    re
    1.18
    4
    1.17
    ।
    1.16
    ，
    1.12
    。
    1.12
    for
    1.11
    POSITIVE LOGITS
    ك
    1.20
    স
    1.16
    ла
    1.10
     работы
    1.10
    خ
    1.04
    લ
    1.04
    ()},
    1.00
    ت
    0.96
    ות
    0.95
    تش
    0.95
    Activations Density 0.000%

    No Known Activations