© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214612
    Prev
    Next
    INDEX
    Explanations

    ;; comments

    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_5_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
    ン
    1.25
    .
    1.07
     it
    1.05
    kým
    1.03
    mış
    1.02
    ið
    0.98
     Ayers
    0.96
     Física
    0.96
    濩
    0.94
    ਰ
    0.93
    POSITIVE LOGITS
    é
    1.23
    ak
    1.04
    ח
    1.01
     sintomi
    0.97
    il
    0.95
    í
    0.95
    ৩
    0.95
    im
    0.93
    ও
    0.93
     року
    0.92
    Activations Density 0.001%

    No Known Activations