© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209276
    Prev
    Next
    INDEX
    Explanations

    prevents from crashing

    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_20_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
    祭
    0.44
     Definitely
    0.43
    Definitely
    0.42
    汙
    0.42
     Thursday
    0.40
     definitivamente
    0.40
     proti
    0.40
    원의
    0.40
     frescos
    0.39
     olt
    0.39
    POSITIVE LOGITS
    actionBarTab
    0.47
    ULTY
    0.45
    Popover
    0.43
    โป
    0.41
    𠃍
    0.41
    ianSpace
    0.40
    큘
    0.40
    偻
    0.40
     TAKE
    0.40
    ጣጠ
    0.40
    Activations Density 0.005%

    No Known Activations