© 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. 79160
    Prev
    Next
    INDEX
    Explanations

    unsigned integer types

    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
     honest
    0.41
    킵
    0.39
     stripe
    0.38
     Camero
    0.38
    ook
    0.37
    stripe
    0.37
     Stripe
    0.37
    honest
    0.36
     stripes
    0.36
     改
    0.36
    POSITIVE LOGITS
     wymaga
    0.37
     ഇന്ന
    0.36
    สี
    0.35
    さら
    0.35
    четов
    0.35
    лем
    0.35
     sustains
    0.35
     hemi
    0.34
    Required
    0.33
     overflows
    0.33
    Activations Density 0.002%

    No Known Activations