© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61823
    Prev
    Next
    INDEX
    Explanations

    speech recognition

    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_11_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
     man
    0.57
    ean
    0.57
     f
    0.57
     (
    0.57
    ximity
    0.57
     Helium
    0.55
    ּ
    0.55
    equity
    0.55
     Homes
    0.54
     Hol
    0.54
    POSITIVE LOGITS
    օ
    0.63
    の方法
    0.62
     chiede
    0.53
    ኾ
    0.52
    麪
    0.50
     менедж
    0.50
    ogène
    0.49
     навіть
    0.49
     руководитель
    0.49
     кандай
    0.48
    Activations Density 0.005%

    No Known Activations