© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46159
    Prev
    Next
    INDEX
    Explanations

    distracts from

    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
     congratulated
    0.58
     gratification
    0.57
    Coref
    0.57
    建造
    0.55
    ведена
    0.55
     그냥
    0.55
    ാ
    0.54
    ø
    0.54
     живе
    0.53
     deregulation
    0.52
    POSITIVE LOGITS
    Hector
    0.54
    はじめ
    0.50
    Scottish
    0.47
    Western
    0.47
    Hell
    0.46
     Scottish
    0.45
    thern
    0.45
    ությ
    0.44
    clen
    0.44
    䣼
    0.43
    Activations Density 0.002%

    No Known Activations