© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83354
    Prev
    Next
    INDEX
    Explanations

    assigning numerical IDs

    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_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notation
    0.41
    ቀ
    0.39
    കളും
    0.39
     greets
    0.39
    രുദ്ധ
    0.37
    notation
    0.36
    ufig
    0.36
    স্পতিবার
    0.35
     Notation
    0.35
    ጋገብ
    0.35
    POSITIVE LOGITS
     Stitch
    0.43
     BECAUSE
    0.42
     экспери
    0.41
    䪱
    0.39
     stitching
    0.39
     Cornerstone
    0.38
    选
    0.38
    ോ
    0.38
    因为
    0.37
    VICIO
    0.37
    Activations Density 0.013%

    No Known Activations