© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154610
    Prev
    Next
    INDEX
    Explanations

    equal to

    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_23_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
     osmosis
    0.42
     aux
    0.42
    Health
    0.41
     =====
    0.40
     Health
    0.39
     mores
    0.38
     فش
    0.38
     thấm
    0.38
     به‌
    0.38
     Hoffman
    0.38
    POSITIVE LOGITS
    ujem
    0.45
     CMA
    0.43
    hutang
    0.43
    丼
    0.43
    ены
    0.42
    wen
    0.40
    ственное
    0.40
    DRA
    0.40
     bicara
    0.39
    UEN
    0.39
    Activations Density 0.000%

    No Known Activations