© 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. 90201
    Prev
    Next
    INDEX
    Explanations

    player destinations

    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
     которые
    0.45
     एसएसपी
    0.42
    恜
    0.42
     brilh
    0.42
    Hom
    0.41
     които
    0.41
     жены
    0.41
     których
    0.40
     추천
    0.40
     ڕ
    0.40
    POSITIVE LOGITS
    che
    0.41
    欬
    0.40
    creation
    0.39
    we
    0.38
     Clover
    0.38
     exists
    0.37
    Could
    0.37
     Rover
    0.37
    announce
    0.36
    ayd
    0.36
    Activations Density 0.000%

    No Known Activations