© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243451
    Prev
    Next
    INDEX
    Explanations

    matplotlib plots

    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_40_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
     输入
    0.40
    ีก
    0.39
    FFIC
    0.39
    Bolt
    0.38
    zag
    0.38
    मु
    0.37
    InputChange
    0.37
    鹂
    0.36
    याम
    0.36
    蓍
    0.36
    POSITIVE LOGITS
     subsistence
    0.37
     arcade
    0.37
     surfaces
    0.36
    udades
    0.36
    藏
    0.36
     procure
    0.36
    uca
    0.36
     Elf
    0.36
    ândia
    0.36
     Idani
    0.35
    Activations Density 0.000%

    No Known Activations