© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3919
    Prev
    Next
    INDEX
    Explanations

    2-3, 4-6, 7-8

    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
     brute
    0.38
    ুনে
    0.37
    坆
    0.36
    ="#">
    0.35
    常见
    0.35
    ່
    0.35
    /';
    0.34
    \";
    0.33
     اړ
    0.33
    `;
    0.33
    POSITIVE LOGITS
    –
    0.55
    ~
    0.55
    ～
    0.54
     ~
    0.50
    〜
    0.48
    ∼
    0.43
     ～
    0.42
     to
    0.41
     až
    0.39
    乃至
    0.39
    Activations Density 0.250%

    No Known Activations