© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193513
    Prev
    Next
    INDEX
    Explanations

    group composition

    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_27_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
    🦑
    0.42
    श्विक
    0.42
     ventures
    0.41
     दशकों
    0.41
     ಸುದ್ದ
    0.40
     Están
    0.40
     दंप
    0.38
    .$,
    0.37
     روشنی
    0.37
    表演
    0.37
    POSITIVE LOGITS
     watered
    0.37
    Chrys
    0.36
    Ange
    0.35
     vaja
    0.35
    paintbrush
    0.34
     생긴
    0.34
     AssertionError
    0.33
    입
    0.32
    पित
    0.32
     হাতের
    0.32
    Activations Density 0.001%

    No Known Activations