© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58595
    Prev
    Next
    INDEX
    Explanations

    bilibili, meat, flat, 软件, massagers, welfare

    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
    ۸
    0.59
    niveau
    0.54
     Бекер
    0.53
    ലോ
    0.50
    Chúng
    0.50
     ήταν
    0.50
    Nous
    0.48
    焼け
    0.48
    ۱
    0.47
    thrown
    0.46
    POSITIVE LOGITS
    ed
    0.49
     silently
    0.48
     carefully
    0.46
    鳄
    0.46
     prioritize
    0.46
     excerpt
    0.46
     అన్ని
    0.45
    ác
    0.45
     calmly
    0.45
     dangling
    0.45
    Activations Density 0.011%

    No Known Activations