© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105938
    Prev
    Next
    INDEX
    Explanations

    calaveras county, ceratosaurus, garcia's restaurant

    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_1_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
    '
    1.05
    كبر
    1.02
     it
    0.98
    يارات
    0.97
     ersch
    0.96
     cataly
    0.95
     hypothes
    0.92
     branca
    0.92
     emargin
    0.90
     erud
    0.89
    POSITIVE LOGITS
    I
    1.12
    ↵
    1.07
    th
    1.05
    다
    0.97
    is
    0.96
    の詳細
    0.92
    ли
    0.92
    де
    0.90
    ो
    0.89
    T
    0.88
    Activations Density 0.001%

    No Known Activations