© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156911
    Prev
    Next
    INDEX
    Explanations

    emisión

    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_2_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
     мъ
    1.11
    ード
    1.02
     allemand
    1.00
    ุ
    0.97
     αρχ
    0.96
    i
    0.93
     έγ
    0.93
     каким
    0.92
     ανά
    0.91
     жы
    0.91
    POSITIVE LOGITS
    ন
    1.45
    ע
    1.39
    е
    1.34
    н
    1.31
     as
    1.25
    你
    1.21
    ن
    1.20
    ви
    1.17
    é
    1.13
    اری
    1.13
    Activations Density 0.002%

    No Known Activations