© 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. 246667
    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
     realista
    0.44
    bleshooting
    0.44
    tbLabel
    0.43
    एमसी
    0.40
     enfrent
    0.39
     kabul
    0.39
     digitales
    0.39
    畬
    0.39
     facing
    0.38
    Specifications
    0.38
    POSITIVE LOGITS
    tell
    0.46
    work
    0.45
     work
    0.40
     join
    0.39
    join
    0.39
     tell
    0.38
    lán
    0.37
     periodic
    0.37
    telling
    0.37
    út
    0.37
    Activations Density 0.001%

    No Known Activations