© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86219
    Prev
    Next
    INDEX
    Explanations

    scantily clad

    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_3_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
    på
    0.68
    más
    0.67
    nement
    0.66
    
    0.64
    ب
    0.61
     an
    0.61
     في
    0.60
    рија
    0.60
    ni
    0.59
     leis
    0.59
    POSITIVE LOGITS
    RO
    0.74
    IE
    0.73
    OF
    0.70
    0
    0.70
    OC
    0.69
    IN
    0.68
    OM
    0.68
    them
    0.68
    LL
    0.67
    )$:
    0.66
    Activations Density 0.000%

    No Known Activations