© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79944
    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_0_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
    л
    0.86
    ر
    0.80
    ل
    0.75
    ز
    0.69
     as
    0.67
    лії
    0.66
    discuss
    0.63
     wichtige
    0.61
    لما
    0.61
    ну
    0.61
    POSITIVE LOGITS
    )
    0.85
    ]
    0.70
    re
    0.66
    y
    0.64
     resur
    0.63
    m
    0.63
    ן
    0.62
    ۵
    0.62
     balm
    0.62
    }
    0.61
    Activations Density 0.000%

    No Known Activations