© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133694
    Prev
    Next
    INDEX
    Explanations

    unnerved, название проекта

    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_1_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
    י
    1.34
    ların
    1.11
    し
    1.09
    ి
    1.09
    ی
    1.09
    s
    1.06
    お知らせ
    1.04
    ா
    1.02
    ترین
    1.02
    おそらく
    1.02
    POSITIVE LOGITS
    ai
    1.27
    -
    1.24
    1.21
     as
    1.09
     (
    1.02
    Registro
    1.02
    el
    0.99
     سي
    0.98
    وي
    0.95
    Usuario
    0.95
    Activations Density 0.000%

    No Known Activations