© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216203
    Prev
    Next
    INDEX
    Explanations

    comma-separated values

    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
     comma
    0.78
    comma
    0.63
    Comma
    0.61
     commas
    0.49
    複数
    0.48
     multiple
    0.46
     ",",
    0.44
    逗
    0.44
    Multiple
    0.43
    多个
    0.43
    POSITIVE LOGITS
     ತು
    0.38
     swung
    0.36
    ähne
    0.35
    Swing
    0.35
    lwjglVersion
    0.35
    swing
    0.33
    しくは
    0.33
    ủy
    0.33
    childComplexity
    0.32
     colouring
    0.32
    Activations Density 0.028%

    No Known Activations