© 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. 206003
    Prev
    Next
    INDEX
    Explanations

    critically acclaimed media

    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
    िकाओं
    0.50
    Fram
    0.42
     महाविद्या
    0.42
    鉗
    0.40
    minecraft
    0.40
     сердца
    0.40
     Frontiers
    0.39
    ricies
    0.39
    塢
    0.39
    द्वारे
    0.39
    POSITIVE LOGITS
     GAZ
    0.49
     muzik
    0.43
     CEL
    0.43
     ARN
    0.41
     KLM
    0.41
     Ал
    0.41
     Duy
    0.41
    贔
    0.40
    龶
    0.40
    locale
    0.40
    Activations Density 0.001%

    No Known Activations