© 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. 112421
    Prev
    Next
    INDEX
    Explanations

    or, at, a, and, of, >, 使用, you, A, %

    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
     предполагает
    1.23
    j
    1.17
    в
    1.11
    га
    1.10
    un
    1.09
    мимо
    1.07
    с
    1.03
    𝐠
    0.99
    де
    0.99
    gruppen
    0.99
    POSITIVE LOGITS
     or
    1.38
     at
    1.34
     a
    1.24
     and
    1.24
     of
    1.23
    >
    1.18
    使用
    1.17
     you
    1.15
     A
    1.11
    %
    1.06
    Activations Density 0.000%

    No Known Activations