© 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. 78948
    Prev
    Next
    INDEX
    Explanations

    technical specific terms

    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
     Wick
    2.27
    ウィ
    2.23
    wick
    2.19
    WICK
    2.11
     Wicked
    2.09
     wick
    2.03
     위
    1.98
    Wi
    1.93
     ві
    1.88
    WI
    1.87
    POSITIVE LOGITS
    呻
    0.38
    ्यालय
    0.38
     മൂല
    0.37
    脹
    0.37
    roveň
    0.35
     vas
    0.35
     Vas
    0.35
     vacun
    0.34
     vattati
    0.34
     நாக
    0.34
    Activations Density 0.054%

    No Known Activations