© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52561
    Prev
    Next
    INDEX
    Explanations

    browser APIs, airplane mode, handles, cookies, based

    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_31_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
     exhausts
    0.39
     йөк
    0.35
     exhaustion
    0.35
    FromArray
    0.35
    倣
    0.35
    青山
    0.35
    comic
    0.34
     spl
    0.34
    叅
    0.34
    പ്പിക്കുന്ന
    0.34
    POSITIVE LOGITS
     Safari
    0.45
     Cookies
    0.45
     cookies
    0.42
    ifice
    0.41
    WebKit
    0.41
    uture
    0.41
     Window
    0.40
    Cookies
    0.40
    WindowState
    0.39
    uterte
    0.39
    Activations Density 0.155%

    No Known Activations