© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 149121
    Prev
    Next
    INDEX
    Explanations

    void

    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_59_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
    GO
    0.45
     //-
    0.44
    Go
    0.40
    Close
    0.40
     ))->
    0.39
    Ž
    0.39
     "]");
    0.39
    LER
    0.38
    IGR
    0.38
    Printf
    0.38
    POSITIVE LOGITS
    {
    0.55
     findAll
    0.54
    :*
    0.51
    ,*
    0.50
    *(
    0.49
    *
    0.48
     condemn
    0.47
    {*
    0.46
    *[
    0.45
     gameState
    0.45
    Activations Density 0.002%

    No Known Activations