© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8581
    Prev
    Next
    INDEX
    Explanations

    limit and convergence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    ovis
    0.39
    iazza
    0.38
     ойно
    0.36
     остан
    0.36
    ➛
    0.36
     Hus
    0.36
    tin
    0.35
    хин
    0.35
    ↣
    0.35
    kub
    0.35
    POSITIVE LOGITS
     limit
    2.39
     Limit
    2.14
    limit
    2.11
    Limit
    2.11
     limiting
    2.06
     limite
    1.99
     Lim
    1.98
     lim
    1.96
    lim
    1.95
    Lim
    1.95
    Activations Density 0.055%

    No Known Activations