© 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. 8319
    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
    公正
    0.45
     walnuts
    0.35
    ଘ
    0.35
     гла
    0.35
     fairs
    0.34
    akumar
    0.34
    稻
    0.34
    笊
    0.34
    槤
    0.34
     nik
    0.33
    POSITIVE LOGITS
    foot
    0.58
    Foot
    0.58
     foot
    0.56
    FOOT
    0.52
     Foot
    0.52
     pieds
    0.49
     footer
    0.44
     pés
    0.43
    Footer
    0.43
    footer
    0.43
    Activations Density 0.033%

    No Known Activations