© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232004
    Prev
    Next
    INDEX
    Explanations

    Gouache, Gouging, Gouda

    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_6_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
    .
    0.95
    мого
    0.93
     thérapeutique
    0.93
     público
    0.92
     assent
    0.92
     inroads
    0.91
     améli
    0.91
     previsão
    0.90
    рії
    0.89
     escánd
    0.88
    POSITIVE LOGITS
    。
    1.28
    to
    1.17
    ين
    1.13
    ।
    1.09
    ut
    1.09
    s
    1.05
    '
    1.05
    '।
    1.03
    ی
    1.02
    ри
    1.01
    Activations Density 0.000%

    No Known Activations