© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139629
    Prev
    Next
    INDEX
    Explanations

    COPPA Privacy Protection

    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_12_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
    oba
    0.54
    th
    0.52
     مختلف
    0.50
     छन्
    0.49
     different
    0.49
    H
    0.49
    day
    0.48
    aha
    0.48
     कौनसा
    0.48
     lighter
    0.48
    POSITIVE LOGITS
    ed
    0.56
    ing
    0.54
    ęła
    0.54
    ශ
    0.52
     construe
    0.52
    arım
    0.50
     overcame
    0.50
    Ꭵ
    0.48
     पैरों
    0.48
     angered
    0.48
    Activations Density 0.001%

    No Known Activations