© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142062
    Prev
    Next
    INDEX
    Explanations

    Haleakala, Srinagar, Poon

    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_0_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
    ب
    2.02
    ק
    1.88
    lə
    1.88
    ल
    1.78
    ล
    1.73
    م
    1.68
    า
    1.60
    म
    1.56
    ل
    1.55
    د
    1.55
    POSITIVE LOGITS
    "
    1.73
    <0x91>
    1.34
     مي
    1.25
     السي
    1.16
     وزير
    1.16
     غير
    1.14
     لي
    1.13
    ”
    1.11
     الدرا
    1.08
     komen
    1.06
    Activations Density 0.000%

    No Known Activations