© 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. 18901
    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
    昨
    0.37
    苟
    0.37
     regenerate
    0.37
     Burt
    0.36
     मद
    0.36
     recreate
    0.35
     renin
    0.35
     फ्रै
    0.34
     locating
    0.34
    ☢
    0.34
    POSITIVE LOGITS
    ibilidades
    0.44
    maline
    0.41
    Voy
    0.40
    Crow
    0.40
     reconocimiento
    0.38
    Belt
    0.38
    neos
    0.38
     заряда
    0.37
     Crow
    0.37
    MAL
    0.37
    Activations Density 0.000%

    No Known Activations