© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220485
    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_31_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
     позволи
    0.40
     невероят
    0.35
    ノート
    0.35
    酐
    0.33
    றி
    0.33
     permitem
    0.33
    ColorScheme
    0.32
     приносит
    0.32
     Миха
    0.32
    hydrocèle
    0.32
    POSITIVE LOGITS
    mess
    0.43
    ႃ
    0.40
     przest
    0.37
    alum
    0.37
     Mess
    0.36
     timeout
    0.36
     옛
    0.36
     graduation
    0.36
     առ
    0.35
     Мат
    0.35
    Activations Density 0.000%

    No Known Activations