© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 134388
    Prev
    Next
    INDEX
    Explanations

    code punctuation and language markers

    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_37_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
    žený
    0.39
     پت
    0.38
    Sig
    0.38
     shelters
    0.37
    ToolStrip
    0.37
     garages
    0.37
    輌
    0.36
    fdata
    0.35
    푠
    0.35
    銀
    0.35
    POSITIVE LOGITS
     voce
    0.40
    FindAsync
    0.38
    ;;
    0.37
    )?;
    0.37
     seize
    0.36
    );
    0.36
    ओके
    0.36
     Nhân
    0.35
    anesu
    0.35
    )$;
    0.34
    Activations Density 0.000%

    No Known Activations