© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13093
    Prev
    Next
    INDEX
    Explanations

    brute force, odds, chance

    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_13_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
    ുകളും
    0.19
     नाइट्रेट
    0.19
    Ⲕ
    0.19
     Maynard
    0.18
     owls
    0.18
    ඉ
    0.17
     Küchen
    0.17
     활용
    0.17
     어디
    0.17
    requenz
    0.17
    POSITIVE LOGITS
     behavior
    0.21
    ed
    0.19
    ↵↵↵
    0.18
    aila
    0.18
    '
    0.18
    oris
    0.17
     negotiation
    0.16
    an
    0.16
    leva
    0.16
     behaviors
    0.16
    Activations Density 0.037%

    No Known Activations