© 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. 40961
    Prev
    Next
    INDEX
    Explanations

    dynamic display solutions awards

    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
    kep
    0.61
    stieg
    0.61
     ﺍ
    0.59
     ASSESSMENT
    0.58
     adecuado
    0.57
     ОБ
    0.57
    
    0.57
     importante
    0.55
     ООО
    0.55
     régulière
    0.55
    POSITIVE LOGITS
     an
    0.89
    an
    0.87
    ى
    0.84
    u
    0.77
    ان
    0.75
    ע
    0.73
    ur
    0.73
    a
    0.66
     to
    0.65
    ো
    0.63
    Activations Density 0.017%

    No Known Activations