© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84089
    Prev
    Next
    INDEX
    Explanations

    управление двигателем

    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_0_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
    at
    2.05
    and
    1.91
    in
    1.66
    ig
    1.52
    s
    1.48
    ’
    1.38
    as
    1.37
    ю
    1.36
    é
    1.34
    నూ
    1.34
    POSITIVE LOGITS
     you
    1.40
    𝗯
    1.34
    म
    1.25
    いが
    1.20
    ाये
    1.20
     this
    1.18
    یاء
    1.17
    는데
    1.16
    دی
    1.14
    り
    1.13
    Activations Density 0.000%

    No Known Activations