© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29479
    Prev
    Next
    INDEX
    Explanations

    lightGBM, litecoin, LiteSpeed

    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_40_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
     Revel
    0.45
    éor
    0.39
    PROOF
    0.39
    Revel
    0.39
     Einf
    0.38
     돌
    0.37
    wrs
    0.37
     pounded
    0.37
    पंच
    0.36
    Punch
    0.35
    POSITIVE LOGITS
    ebox
    0.37
     $<$
    0.37
    чению
    0.37
     डिप्टी
    0.36
     API
    0.36
    cimento
    0.36
    ுக
    0.35
    箱
    0.34
    ebo
    0.34
    对外
    0.34
    Activations Density 0.002%

    No Known Activations