© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39640
    Prev
    Next
    INDEX
    Explanations

    def

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    i
    0.77
    י
    0.69
    ي
    0.66
    ി
    0.59
    ে
    0.56
    ი
    0.55
    ी
    0.55
    ி
    0.53
    ి
    0.50
    يّ
    0.45
    POSITIVE LOGITS
    咲
    0.37
    ඉ
    0.35
    anted
    0.34
     Asher
    0.34
     থাক
    0.34
    鑣
    0.34
    Swift
    0.34
     선물
    0.33
     Javascript
    0.33
    ద్ర
    0.33
    Activations Density 0.000%

    No Known Activations