© 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. 130610
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ,
    1.17
    ли
    1.11
    ;
    1.06
    1
    1.05
    ied
    1.05
    ico
    1.02
    acking
    1.01
    ant
    0.95
    ischen
    0.95
    ad
    0.93
    POSITIVE LOGITS
    ни
    1.11
     narcot
    0.97
    ﺖ
    0.96
    a
    0.95
     što
    0.95
     difficoltà
    0.94
    ע
    0.93
    ના
    0.92
    ને
    0.91
    া
    0.91
    Activations Density 0.000%

    No Known Activations