© 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. 3619
    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
    댐
    0.45
    ersion
    0.42
     IEC
    0.42
     modellen
    0.40
     intelekt
    0.40
     Models
    0.40
    зи
    0.39
    აწილ
    0.38
     bilgi
    0.38
     Verdun
    0.38
    POSITIVE LOGITS
     winemaker
    0.37
     रेंज
    0.36
    ENDOR
    0.35
    خان
    0.35
    鹵
    0.35
     vivos
    0.35
     Underwater
    0.35
     एनिमल
    0.34
     loaders
    0.34
    平方米
    0.33
    Activations Density 0.009%

    No Known Activations