© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210570
    Prev
    Next
    INDEX
    Explanations

    ray Restaurant

    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_10_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
    p
    0.37
    sp
    0.32
    ]).
    0.31
    m
    0.29
    f
    0.29
    a
    0.28
    的力量
    0.27
    mad
    0.26
    q
    0.26
    {(
    0.26
    POSITIVE LOGITS
     želite
    0.30
     что
    0.29
     contestant
    0.28
     производителя
    0.28
     nejsou
    0.28
     која
    0.28
     menino
    0.28
     nové
    0.28
     miasta
    0.28
     nejen
    0.28
    Activations Density 0.000%

    No Known Activations