© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14717
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions

    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_13_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
    zes
    0.39
    ア
    0.38
     umani
    0.38
    </h2>
    0.37
     an
    0.37
    ...</
    0.36
     Ens
    0.36
    ....
    0.36
    人类
    0.36
    ...”
    0.35
    POSITIVE LOGITS
     налого
    0.38
     pigmented
    0.38
     antiguo
    0.37
     Vanden
    0.37
     കിട
    0.37
     Diageo
    0.37
    燡
    0.37
     ಕರಿ
    0.36
    rayed
    0.36
     சுண்ணாம்பு
    0.35
    Activations Density 0.005%

    No Known Activations