© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201021
    Prev
    Next
    INDEX
    Explanations

    ESR

    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_6_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
    \
    1.66
    ش
    1.48
    د
    1.40
    ב
    1.38
    s
    1.35
    (
    1.35
    ?
    1.34
    es
    1.27
    ש
    1.22
     by
    1.20
    POSITIVE LOGITS
     وکړئ
    1.06
     Суриков
    1.03
    ように
    1.02
     Гинд
    0.99
     ”,
    0.95
    ۔
    0.95
    の位置
    0.91
    نید
    0.91
    ”،
    0.91
    hiddenMap
    0.91
    Activations Density 0.000%

    No Known Activations