© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217564
    Prev
    Next
    INDEX
    Explanations

    multiple, distinct, plural

    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_31_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
    ঢাকার
    0.36
    សូម
    0.36
    ទ
    0.35
    Akh
    0.34
    |"
    0.33
     uncooked
    0.33
     retrieved
    0.33
     Documentary
    0.32
    镐
    0.32
     Hutt
    0.32
    POSITIVE LOGITS
    multiple
    0.59
     multiple
    0.54
     Multiple
    0.51
    Multiple
    0.49
    多个
    0.46
     múltiples
    0.45
    複数の
    0.45
     plur
    0.43
    distinct
    0.41
     plural
    0.41
    Activations Density 0.078%

    No Known Activations