© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109174
    Prev
    Next
    INDEX
    Explanations

    yonder or beyonder

    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_1_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
    the
    1.63
    ב
    1.43
    ब
    1.38
    ۔
    1.38
    მ
    1.28
    ール
    1.20
    ме
    1.20
    ना
    1.18
    ，
    1.17
    ו
    1.16
    POSITIVE LOGITS
     in
    1.29
    ية
    1.13
    us
    1.11
    ia
    1.09
    ",
    1.06
     l
    1.01
    ian
    1.00
    ");
    0.95
    ang
    0.91
     g
    0.90
    Activations Density 0.000%

    No Known Activations