© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 5694
    Prev
    Next
    INDEX
    Explanations

    code scaffolding or setup

    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
    /');
    0.41
    ...\
    0.36
    сив
    0.36
    ).\
    0.36
    ):\
    0.35
     டா
    0.35
     {\
    0.34
    細菌
    0.34
    /");
    0.34
    .);
    0.34
    POSITIVE LOGITS
    GroupName
    0.39
     വകു
    0.39
    appName
    0.37
    ᅯ
    0.37
    application
    0.37
    rice
    0.36
    アプリケーション
    0.36
     certified
    0.35
     effective
    0.35
     application
    0.35
    Activations Density 0.023%

    No Known Activations