© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39530
    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_11_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
     noy
    0.47
     weakened
    0.44
     судо
    0.44
    ou
    0.43
     pressed
    0.43
     weakens
    0.42
     उस
    0.42
    ’
    0.42
    oub
    0.41
    rec
    0.41
    POSITIVE LOGITS
     ilmiah
    0.55
    Как
    0.49
     бое
    0.49
     deti
    0.48
    ত্রিম
    0.48
    தேசம்
    0.48
    På
    0.48
     Dokument
    0.47
    ாளர்கள்
    0.47
     menopause
    0.47
    Activations Density 0.000%

    No Known Activations