© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36581
    Prev
    Next
    INDEX
    Explanations

    tulipmania

    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_3_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
    یل
    0.88
    t
    0.88
    )
    0.85
    に使
    0.79
    د
    0.76
     summar
    0.75
    diam
    0.75
    یت
    0.74
     UML
    0.72
    careers
    0.71
    POSITIVE LOGITS
    ة
    0.94
    يد
    0.90
    at
    0.86
    يدات
    0.76
    IS
    0.71
    كيد
    0.71
    يه
    0.71
    ת
    0.71
    as
    0.68
    يكون
    0.68
    Activations Density 0.001%

    No Known Activations