© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198367
    Prev
    Next
    INDEX
    Explanations

    disclaimer

    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_9_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
    湋
    0.54
    ার্ড
    0.50
     Accountants
    0.50
     الأ
    0.49
     লাগ
    0.47
     เช
    0.46
     Restaur
    0.46
     dẫn
    0.45
     trimethyl
    0.44
    堞
    0.44
    POSITIVE LOGITS
    SuppressWarnings
    0.47
    X
    0.46
    undum
    0.45
    atamente
    0.45
     goma
    0.45
    J
    0.44
    ه‌ی
    0.43
    um
    0.43
    ab
    0.43
    IN
    0.43
    Activations Density 0.000%

    No Known Activations