© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29273
    Prev
    Next
    INDEX
    Explanations

    max pooling layer, Conv, Flatten

    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_40_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
    囵
    0.37
     கரி
    0.35
    Vi
    0.35
     recur
    0.34
    温暖
    0.33
     Vi
    0.33
    στ
    0.33
    ('>
    0.33
     ketones
    0.32
     آپریشن
    0.32
    POSITIVE LOGITS
     visitante
    0.37
     പോ
    0.36
     tamu
    0.36
     bund
    0.36
     glaz
    0.36
    NAM
    0.35
    amax
    0.35
     max
    0.35
     brightest
    0.34
     Laj
    0.34
    Activations Density 0.005%

    No Known Activations