© 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. 178937
    Prev
    Next
    INDEX
    Explanations

    shapes

    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
     ба
    1.55
    バ
    1.28
     ba
    1.17
     Ба
    1.15
    ба
    1.13
    巴
    1.12
     Ba
    1.11
     बा
    1.09
     barium
    1.09
    Ба
    1.07
    POSITIVE LOGITS
     па
    0.44
     Paige
    0.41
     PA
    0.41
    CAR
    0.38
    PA
    0.38
    러스
    0.38
    न्दावन
    0.38
    SAFER
    0.37
     آگ
    0.37
    Ago
    0.37
    Activations Density 0.021%

    No Known Activations