© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44607
    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_22_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
    蟶
    0.57
     முதல்வர்
    0.52
     banca
    0.50
     comando
    0.50
    ς
    0.50
     असतो
    0.48
    ู่
    0.48
     விமான
    0.48
     rosto
    0.48
     firewall
    0.47
    POSITIVE LOGITS
    y
    0.63
     P
    0.61
    P
    0.58
    Green
    0.52
    ig
    0.51
     areas
    0.50
    Staff
    0.50
     Areas
    0.49
    K
    0.49
    ot
    0.49
    Activations Density 0.000%

    No Known Activations