© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59666
    Prev
    Next
    INDEX
    Explanations

    audio amplification and noise cancellation

    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_11_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
    澫
    0.39
    meye
    0.39
    節目
    0.37
     Partizan
    0.37
     TESTING
    0.37
    τηση
    0.36
    ಾರ್ಟ
    0.36
    ితో
    0.36
     OTHERWISE
    0.36
     परीक्षण
    0.34
    POSITIVE LOGITS
    ER
    0.45
    ED
    0.39
    .,
    0.37
    ^{\
    0.34
    IE
    0.34
    ;
    0.34
    ্র
    0.34
    ří
    0.33
    อัน
    0.33
    ']
    0.32
    Activations Density 0.032%

    No Known Activations