© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4201
    Prev
    Next
    INDEX
    Explanations

    game, mission, program, or test details

    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_39_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
     स्रोत
    0.47
     स्रो
    0.44
    actoring
    0.42
     कनेक्टिव
    0.40
    成绩
    0.40
    初始
    0.40
    坻
    0.39
     कनेक्टिविटी
    0.39
    仪器
    0.39
    棱
    0.39
    POSITIVE LOGITS
     specifics
    0.49
     format
    0.49
     Specific
    0.48
     description
    0.47
     desc
    0.47
     specific
    0.47
     simulation
    0.45
     details
    0.45
     formats
    0.45
     particulars
    0.44
    Activations Density 0.078%

    No Known Activations