© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49899
    Prev
    Next
    INDEX
    Explanations

    Texas Instruments

    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_10_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
    ä
    0.89
     ي
    0.68
    nu
    0.67
    elling
    0.66
    yn
    0.64
    li
    0.63
     ف
    0.63
    ra
    0.62
     ث
    0.62
    نة
    0.61
    POSITIVE LOGITS
    in
    0.63
    が高い
    0.61
    InData
    0.57
    ख्ती
    0.57
     sebesar
    0.57
    ブログ
    0.54
     dikatakan
    0.53
    ബരിമല
    0.53
    Inte
    0.53
     talaga
    0.53
    Activations Density 0.000%

    No Known Activations