© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156853
    Prev
    Next
    INDEX
    Explanations

    varied

    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_2_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
    ي
    1.88
    ра
    1.53
    י
    1.39
    ا
    1.26
    i
    1.23
    ми
    1.19
    на
    1.13
    t
    1.13
    re
    1.09
    at
    1.05
    POSITIVE LOGITS
    !
    1.17
    M
    1.15
     (
    1.14
    og
    1.13
     be
    1.11
    T
    1.04
     have
    1.03
    ?
    1.03
     a
    1.02
     innovate
    0.98
    Activations Density 0.001%

    No Known Activations