© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89665
    Prev
    Next
    INDEX
    Explanations

    Names

    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_60_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
     primitives
    0.38
     vener
    0.37
     stories
    0.35
     ({
    0.35
     interface
    0.34
     '='
    0.34
     convexity
    0.34
     continuation
    0.33
     unused
    0.33
     empir
    0.33
    POSITIVE LOGITS
    诲
    0.46
    ව
    0.41
     carros
    0.40
    Italia
    0.38
    claves
    0.38
    éis
    0.38
    Essential
    0.38
    erts
    0.37
     Eat
    0.37
    化
    0.37
    Activations Density 0.000%

    No Known Activations