© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195569
    Prev
    Next
    INDEX
    Explanations

    vibrators, timers, or signals

    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_15_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
    ur
    0.57
     Children
    0.53
    owo
    0.47
    IR
    0.46
    I
    0.46
    at
    0.46
    近日
    0.46
    j
    0.45
    AK
    0.44
    SdkVersion
    0.44
    POSITIVE LOGITS
     phụ
    0.54
    cY
    0.52
     நம்பிக்க
    0.50
     технических
    0.49
     cacti
    0.49
    𒋫
    0.49
     scars
    0.49
    даги
    0.48
    серва
    0.48
    MSFontService
    0.47
    Activations Density 0.000%

    No Known Activations