© 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. 34297
    Prev
    Next
    INDEX
    Explanations

    acetophenone, illness, or Hindi/Spanish phrases

    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
    afe
    0.99
    a
    0.94
    ed
    0.93
    es
    0.84
    os
    0.78
     والاح
    0.74
    了他
    0.70
    ه
    0.69
    ROME
    0.68
    もら
    0.68
    POSITIVE LOGITS
    и
    1.13
    ค
    1.01
    ক
    1.00
    트
    0.95
    ร
    0.89
    پ
    0.88
    ری
    0.83
    क
    0.81
    아
    0.81
    б
    0.80
    Activations Density 0.007%

    No Known Activations