© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10296
    Prev
    Next
    INDEX
    Explanations

    conservative

    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_13_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
     varje
    0.48
    River
    0.47
     Raven
    0.47
     RIVER
    0.47
     Diwali
    0.46
     offseason
    0.45
     ([
    0.44
    Resolver
    0.44
     ([[
    0.43
    Chev
    0.43
    POSITIVE LOGITS
    conservative
    0.58
     conservative
    0.58
     patty
    0.53
     સલા
    0.53
     focussing
    0.52
     patties
    0.49
    ológicos
    0.48
    y
    0.47
     innovación
    0.46
    o
    0.46
    Activations Density 0.096%

    No Known Activations