© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147614
    Prev
    Next
    INDEX
    Explanations

    th

    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_59_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
     thoroughly
    1.79
    徹底
    1.18
    彻底
    1.16
     Thorough
    0.81
    Com
    0.43
    鼗
    0.40
     যাবতীয়
    0.38
    COM
    0.38
    Τ
    0.38
    褐
    0.37
    POSITIVE LOGITS
    uly
    0.45
    ully
    0.42
    ian
    0.40
    unya
    0.39
    ur
    0.37
     놓고
    0.36
    ya
    0.36
    rically
    0.36
    계
    0.35
    ate
    0.35
    Activations Density 0.000%

    No Known Activations