© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108539
    Prev
    Next
    INDEX
    Explanations

    cholest, fecal, atl, joj

    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
     be
    1.26
    (
    1.25
    ing
    1.18
    ني
    1.12
    -
    1.11
     de
    1.09
     begin
    1.02
     reflect
    1.02
    ة
    1.02
    ↵
    0.99
    POSITIVE LOGITS
    ان
    1.28
    an
    1.17
    re
    1.09
    बी
    0.96
    リ
    0.95
    ב
    0.95
    き
    0.94
    न
    0.93
    น
    0.93
    اری
    0.93
    Activations Density 0.001%

    No Known Activations