© 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. 79837
    Prev
    Next
    INDEX
    Explanations

    transport due to bulk motion

    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
     by
    1.79
    на
    1.73
     for
    1.66
     to
    1.66
    ud
    1.63
    is
    1.61
    x
    1.60
    ش
    1.55
    ans
    1.51
    z
    1.48
    POSITIVE LOGITS
    이다
    1.42
    সহ
    1.28
    로
    1.23
    in
    1.20
    ↵
    1.16
    이라고
    1.16
    K
    1.16
    ມັນ
    1.15
    的结果
    1.13
    Y
    1.13
    Activations Density 0.000%

    No Known Activations