© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81122
    Prev
    Next
    INDEX
    Explanations

    market

    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_53_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
    alt
    0.44
    ock
    0.40
    叮
    0.39
    学び
    0.39
    PLAT
    0.39
     Connolly
    0.38
    hati
    0.38
     infrequently
    0.38
    szak
    0.38
    ждается
    0.37
    POSITIVE LOGITS
     naval
    0.39
     K
    0.37
    取代
    0.37
    ющим
    0.37
    끄
    0.36
     возду
    0.36
     MO
    0.35
    RMSE
    0.35
    高雄
    0.35
     engulf
    0.34
    Activations Density 0.003%

    No Known Activations