© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1020
    Prev
    Next
    INDEX
    Explanations

    java.util collections

    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_39_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
     परेश
    0.41
    mohan
    0.39
     LANA
    0.38
    酸化
    0.38
    слан
    0.37
    槙
    0.37
    পরি
    0.37
    ὖ
    0.36
     Ön
    0.36
    㭂
    0.36
    POSITIVE LOGITS
    asyon
    0.40
    acos
    0.37
    ache
    0.37
    ago
    0.37
     kle
    0.37
    நோய்
    0.35
    MOD
    0.34
    acch
    0.34
    file
    0.34
    Values
    0.33
    Activations Density 0.002%

    No Known Activations