© 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. 205993
    Prev
    Next
    INDEX
    Explanations

    lex followed by hort, icon, mal, frid

    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
    i
    1.54
    ก
    1.45
    c
    1.41
    n
    1.30
    at
    1.20
    the
    1.13
     W
    1.05
    י
    1.05
    ne
    1.03
    in
    1.02
    POSITIVE LOGITS
    ీ
    0.95
    を探
    0.94
    ۰
    0.94
    값이
    0.93
    ０
    0.93
    ۵
    0.93
     alimentaires
    0.90
    蜃
    0.90
    imple
    0.89
    ५
    0.88
    Activations Density 0.001%

    No Known Activations