© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175761
    Prev
    Next
    INDEX
    Explanations

    fluttering, Sequencer, play, product, Pose

    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_20_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
    /
    0.47
    联网
    0.39
    <0x07>
    0.35
     উদ্দিন
    0.34
     строительства
    0.34
     कारखाना
    0.33
    防
    0.33
     опы
    0.32
     этих
    0.32
    |}\
    0.32
    POSITIVE LOGITS
     infinites
    0.40
    Unsere
    0.40
    मीटर
    0.39
     우리의
    0.39
     unserer
    0.38
     Fonts
    0.38
     tubo
    0.38
     nasze
    0.37
    ו
    0.37
    ಃ
    0.37
    Activations Density 0.000%

    No Known Activations