© 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. 199489
    Prev
    Next
    INDEX
    Explanations

    Sz names

    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
     EDS
    0.41
    麟
    0.41
    尻
    0.40
    ksi
    0.39
     Kodi
    0.39
    Leading
    0.39
     PARAM
    0.39
     logarithms
    0.38
     F
    0.37
    லி
    0.37
    POSITIVE LOGITS
     цвето
    0.37
    ıt
    0.36
    向上
    0.36
    imt
    0.36
    业
    0.36
    ohar
    0.35
    altung
    0.35
    erce
    0.35
    env
    0.34
    ంశ
    0.34
    Activations Density 0.000%

    No Known Activations