© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201185
    Prev
    Next
    INDEX
    Explanations

    ExecuteNonQuery

    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_12_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
    ascape
    0.53
     Packages
    0.50
     $
    0.47
     Sticky
    0.47
    imation
    0.47
    pathy
    0.47
    nera
    0.47
    isphere
    0.47
     Spring
    0.46
    package
    0.46
    POSITIVE LOGITS
    ל
    0.60
     о
    0.57
     ο
    0.54
    يل
    0.53
    стойчи
    0.51
    о
    0.49
     oluşan
    0.49
     certamente
    0.48
     minhas
    0.48
    ocl
    0.47
    Activations Density 0.000%

    No Known Activations