© 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. 259994
    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
    CONFIG
    0.47
    ปี
    0.47
    Escape
    0.47
     concours
    0.47
     baisse
    0.47
    িজ
    0.46
    ﻘ
    0.46
    ючись
    0.46
    YYYY
    0.46
    ᓪ
    0.46
    POSITIVE LOGITS
    yim
    0.58
     vegetarian
    0.46
    akai
    0.46
    acic
    0.46
     alkal
    0.45
    asse
    0.44
     Restaurant
    0.43
    \,.
    0.43
    yue
    0.43
     oral
    0.42
    Activations Density 0.000%

    No Known Activations