© 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
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15636
    Prev
    Next
    INDEX
    Explanations

    code structure imports

    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_34_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
     currentGame
    0.44
     //</
    0.43
     *@
    0.40
    BtnPanel
    0.39
     Delaney
    0.38
     startGame
    0.38
     Baltes
    0.38
     Darren
    0.37
     createNative
    0.37
     fraternity
    0.37
    POSITIVE LOGITS
    AST
    0.37
     친
    0.36
    rato
    0.35
    دو
    0.34
    ₹
    0.34
     crushed
    0.34
    ່າ
    0.34
    Diss
    0.34
    姿
    0.33
    Cr
    0.33
    Activations Density 0.002%

    No Known Activations