© 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. 130247
    Prev
    Next
    INDEX
    Explanations

    electricity grid

    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
    icam
    0.48
     Д
    0.43
    Coluna
    0.43
     D
    0.41
    ODE
    0.39
     컬
    0.39
     trat
    0.38
    ٹو
    0.38
    㬰
    0.38
     본격
    0.38
    POSITIVE LOGITS
    ريب
    0.45
    ovskii
    0.43
    hopper
    0.42
     hoop
    0.41
     LSP
    0.40
     hopper
    0.39
     मीणा
    0.39
     Raw
    0.38
     dimas
    0.38
    licas
    0.38
    Activations Density 0.002%

    No Known Activations