© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121596
    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_37_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
     উত্তরে
    0.38
    Flor
    0.37
     fenomeno
    0.36
     ಬಿ
    0.36
     художника
    0.36
    ネス
    0.35
    坌
    0.35
     COD
    0.34
    脈
    0.34
     ప్రభు
    0.34
    POSITIVE LOGITS
     الأمريكية
    0.42
     américain
    0.42
     American
    0.41
     améric
    0.40
     paroles
    0.40
    udge
    0.40
    Inner
    0.38
     mortgagee
    0.38
     inner
    0.37
     convicted
    0.37
    Activations Density 0.000%

    No Known Activations