© 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
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180508
    Prev
    Next
    INDEX
    Explanations

    coordinates or dimensions

    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_29_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
    ouz
    0.38
     compatibility
    0.38
    panion
    0.38
    shipping
    0.37
    chende
    0.37
     放
    0.37
     વપરા
    0.37
    compatibility
    0.37
     ফ
    0.36
    effect
    0.36
    POSITIVE LOGITS
     అర
    0.42
    気温
    0.41
     från
    0.38
    лед
    0.38
    楽しみ
    0.38
    йд
    0.38
    På
    0.37
    attenzione
    0.37
    kult
    0.37
    trimethyl
    0.37
    Activations Density 0.000%

    No Known Activations