© 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. 34267
    Prev
    Next
    INDEX
    Explanations

    ashwagandha

    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
     on
    0.67
    </h3>
    0.64
    tım
    0.62
    
    0.57
    traction
    0.57
     المحاضره
    0.56
     falleció
    0.56
    traffic
    0.54
    cción
    0.54
    ння
    0.54
    POSITIVE LOGITS
    Т
    1.03
    К
    1.01
    م
    0.98
    Y
    0.95
    ل
    0.91
    im
    0.86
    as
    0.85
    ون
    0.85
    य
    0.84
    З
    0.84
    Activations Density 0.008%

    No Known Activations