© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242530
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     numerically
    0.39
    鱈
    0.39
    byshire
    0.37
     Chiu
    0.37
    лесо
    0.35
    ત્મ
    0.35
     numérica
    0.34
    条件的
    0.34
    Olivier
    0.34
     tribal
    0.34
    POSITIVE LOGITS
     déclaration
    0.41
    妊
    0.41
     относи
    0.39
     szüks
    0.39
     попада
    0.38
     Día
    0.37
     müz
    0.37
     doPost
    0.37
     kittens
    0.37
     relatif
    0.36
    Activations Density 0.000%

    No Known Activations