© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171451
    Prev
    Next
    INDEX
    Explanations

    text from pdf

    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
     Ausgang
    0.45
    šli
    0.45
    пь
    0.45
    賠
    0.45
     Наде
    0.45
     respectivos
    0.45
    чение
    0.44
    чения
    0.44
    énagement
    0.44
     रहेगी
    0.44
    POSITIVE LOGITS
    Fet
    0.50
     come
    0.48
     ت
    0.46
     компью
    0.46
     vif
    0.44
     copy
    0.44
     feature
    0.44
     sugger
    0.43
     tag
    0.43
     fre
    0.43
    Activations Density 0.005%

    No Known Activations