© 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. 30332
    Prev
    Next
    INDEX
    Explanations

    even followed by perception/action verb

    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
    На
    0.45
    İ
    0.45
    أ
    0.43
    يا
    0.42
    \
    0.42
    مر
    0.41
    IK
    0.39
    "
    0.39
    И
    0.39
    크
    0.38
    POSITIVE LOGITS
    o
    0.48
    as
    0.46
    า
    0.42
     are
    0.40
     consomm
    0.39
    soever
    0.39
    юць
    0.39
    oners
    0.39
    asă
    0.38
    é
    0.38
    Activations Density 0.007%

    No Known Activations