© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130842
    Prev
    Next
    INDEX
    Explanations

    Government Ontario

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     board
    0.57
    board
    0.50
     O
    0.47
     bord
    0.47
    板
    0.46
     Occ
    0.43
    ⴳ
    0.43
    Board
    0.42
     Oc
    0.42
     boards
    0.42
    POSITIVE LOGITS
     оли
    0.42
    irie
    0.39
    UED
    0.37
     منفی
    0.37
     Colby
    0.36
    Cn
    0.36
    мене
    0.36
    聶
    0.35
    न्व
    0.35
    chl
    0.35
    Activations Density 0.000%

    No Known Activations