© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144864
    Prev
    Next
    INDEX
    Explanations

    moist

    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_0_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
    ל
    2.13
    л
    1.87
    ल
    1.80
    ک
    1.77
    ING
    1.56
    ル
    1.56
    म
    1.54
    á
    1.52
    ী
    1.52
    س
    1.49
    POSITIVE LOGITS
    i
    1.82
    a
    1.73
     in
    1.64
    e
    1.57
     در
    1.43
    that
    1.43
    もら
    1.40
    在
    1.33
    an
    1.31
    and
    1.30
    Activations Density 0.001%

    No Known Activations