© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106992
    Prev
    Next
    INDEX
    Explanations

    небольших, немного

    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
    Negative Logits
    um
    1.52
    <0x0D>
    1.43
    ються
    1.24
    ými
    1.21
    ov
    1.19
    nem
    1.13
    ode
    1.12
     œufs
    1.12
    owane
    1.09
    nels
    1.08
    POSITIVE LOGITS
    ன்
    1.13
    л
    1.13
    های
    1.09
    ש
    1.09
    기
    1.09
    지는
    1.07
    ר
    1.07
    지를
    1.06
    או
    1.02
    もの
    1.01
    Activations Density 0.000%

    No Known Activations