© 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. 39998
    Prev
    Next
    INDEX
    Explanations

    char_to_index mapping

    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
    面
    0.64
     والج
    0.62
    ፈላ
    0.58
     والك
    0.58
     وع
    0.57
    يه
    0.56
     Фургал
    0.55
    াপা
    0.54
     والأ
    0.54
    कामा
    0.54
    POSITIVE LOGITS
     Cincinnati
    0.57
    ş
    0.54
    w
    0.53
     Albanese
    0.52
    sl
    0.52
    บาง
    0.52
    sh
    0.51
    邸
    0.51
    ഗി
    0.50
    ו
    0.50
    Activations Density 0.020%

    No Known Activations