© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139751
    Prev
    Next
    INDEX
    Explanations

    key derivation function

    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_37_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
     rotational
    0.39
     deepened
    0.38
     administr
    0.38
    柽
    0.38
    जन्म
    0.37
    Plane
    0.36
     lex
    0.35
    люми
    0.35
    ScrollPane
    0.34
     lexicon
    0.34
    POSITIVE LOGITS
    味
    0.42
     Voss
    0.39
     Finding
    0.39
    医
    0.39
     Employment
    0.38
    セント
    0.38
    味的
    0.38
     Henderson
    0.37
     каб
    0.37
    𐰃
    0.37
    Activations Density 0.004%

    No Known Activations