© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147265
    Prev
    Next
    INDEX
    Explanations

    Of

    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
    opers
    0.42
    تها
    0.39
    oll
    0.38
     Obviously
    0.38
     otr
    0.37
    ]<?
    0.37
    (?
    0.37
    ते
    0.36
    ?,
    0.36
    ¹,
    0.36
    POSITIVE LOGITS
     course
    1.33
    course
    1.16
    Course
    1.15
     Course
    1.12
     COURSE
    1.02
     curso
    0.98
    コース
    0.98
    COURSE
    0.96
     курс
    0.95
     कोर्स
    0.92
    Activations Density 0.001%

    No Known Activations