© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174345
    Prev
    Next
    INDEX
    Explanations

    "(" following "Image" or "Text"

    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_20_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
    懑
    0.47
    ijiet
    0.47
     bevat
    0.45
    NewDecoder
    0.45
     ampio
    0.45
    
    0.45
    istir
    0.44
    ฟา
    0.44
     ampia
    0.44
    喺
    0.43
    POSITIVE LOGITS
     плане
    0.45
     succeeded
    0.43
     succeeds
    0.43
    су
    0.41
     Something
    0.41
     ot
    0.40
     focus
    0.39
    тельства
    0.39
    常
    0.39
     movements
    0.39
    Activations Density 0.001%

    No Known Activations