© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240248
    Prev
    Next
    INDEX
    Explanations

    chosen for reason

    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_25_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
     danos
    0.39
     Caramel
    0.37
     प्रभ
    0.37
     Diagrams
    0.36
     Rouse
    0.36
     compromised
    0.35
    柇
    0.35
     rigid
    0.35
     rodzaj
    0.35
     Plants
    0.34
    POSITIVE LOGITS
    Hosted
    0.42
     obiettivi
    0.40
    ذ
    0.40
    wartz
    0.40
    trashItem
    0.39
    闻
    0.39
    Ecommerce
    0.38
    squeeze
    0.38
    ecommerce
    0.38
    Compatibility
    0.38
    Activations Density 0.002%

    No Known Activations