© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45465
    Prev
    Next
    INDEX
    Explanations

    function completion `->`

    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_22_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
    礼
    0.28
    Wars
    0.27
    服装
    0.27
    粗
    0.27
    DER
    0.27
    Rules
    0.26
    Kiza
    0.26
    Justice
    0.26
    Mass
    0.26
    Journal
    0.26
    POSITIVE LOGITS
    otroph
    0.28
     தேதி
    0.26
     χρόνια
    0.25
    toprule
    0.25
     microcontroller
    0.24
     comenzó
    0.24
     leaks
    0.24
    秚
    0.24
     procrast
    0.24
     ശ്രമ
    0.24
    Activations Density 0.004%

    No Known Activations