© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13720
    Prev
    Next
    INDEX
    Explanations

    Star Wars

    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
     scissors
    0.42
     preseason
    0.42
     handheld
    0.40
    hern
    0.39
    ረ
    0.39
     sig
    0.38
     reaper
    0.38
     prefab
    0.38
     Oakland
    0.37
     prefabricated
    0.37
    POSITIVE LOGITS
    Commands
    0.41
    艐
    0.40
     flashing
    0.39
    Fragment
    0.38
    Slope
    0.38
    cmds
    0.36
    Ĩ
    0.36
     থাকতেন
    0.36
    Caps
    0.35
    Ȼ
    0.35
    Activations Density 0.019%

    No Known Activations