© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208069
    Prev
    Next
    INDEX
    Explanations

    command line prompts

    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_20_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
    [](
    0.31
     используя
    0.30
    powder
    0.29
     [](
    0.29
    aggo
    0.28
    ელია
    0.27
    เพื่อ
    0.27
     segreg
    0.27
    "(
    0.27
    >∕</
    0.26
    POSITIVE LOGITS
     bears
    0.30
     means
    0.30
     Bentley
    0.30
     fuller
    0.29
     éditions
    0.29
     battle
    0.28
     quente
    0.28
     offend
    0.28
    ЕВ
    0.27
     первое
    0.27
    Activations Density 0.006%

    No Known Activations