© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58879
    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_2_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
    inis
    1.23
    ін
    1.12
    ↵
    1.09
    ast
    1.07
     carcinogenic
    1.05
    ine
    1.05
    ीन
    1.02
    им
    1.02
    inin
    1.01
     terrestrial
    1.01
    POSITIVE LOGITS
    م
    1.41
    1.30
    IS
    1.18
    by
    0.93
     Caedwalla
    0.93
    м
    0.93
    chond
    0.91
    ր
    0.91
    AW
    0.90
    writerow
    0.90
    Activations Density 0.000%

    No Known Activations