© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63826
    Prev
    Next
    INDEX
    Explanations

    shoes and brands

    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_46_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
     Uly
    0.42
     مارت
    0.41
     मार्ट
    0.38
     बीपीएससी
    0.38
     throwIf
    0.37
     Hor
    0.37
     ල
    0.37
     Wolfgang
    0.37
     wouldnt
    0.37
    帐
    0.37
    POSITIVE LOGITS
    ೖ
    0.48
    pped
    0.42
    క్ర
    0.40
    Seven
    0.40
    Tp
    0.39
     Illegal
    0.38
    ردو
    0.37
    RAR
    0.36
    Illegal
    0.36
    Syntax
    0.36
    Activations Density 0.008%

    No Known Activations