© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214764
    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_50_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
    ភ្
    0.36
    ிரம்
    0.36
    Brasil
    0.36
     ControllerBase
    0.36
    ört
    0.36
     Thái
    0.36
    -->'
    0.36
    }());
    0.36
     hindu
    0.35
     মিনি
    0.34
    POSITIVE LOGITS
     পঞ্চ
    0.40
    Fur
    0.40
    ających
    0.39
    Casa
    0.39
    规
    0.39
    rule
    0.38
    ógica
    0.38
    ulosa
    0.38
    kiewicz
    0.38
    shiny
    0.38
    Activations Density 0.000%

    No Known Activations