© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106929
    Prev
    Next
    INDEX
    Explanations

    originated in

    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
    開催
    1.31
    3
    1.24
    図
    1.13
    探し
    1.10
    ca
    1.09
    ps
    1.06
    紹介
    1.06
    して
    1.04
    下
    1.02
    設定
    1.00
    POSITIVE LOGITS
     rápida
    1.07
     temprana
    1.00
     matemática
    0.97
     discourses
    0.97
     towers
    0.96
     benthic
    0.96
     múlti
    0.96
     legumes
    0.95
     croissants
    0.95
     presion
    0.94
    Activations Density 0.000%

    No Known Activations