© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1650
    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_40_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
    พ์
    0.38
    뀌
    0.38
    Floral
    0.37
    webkit
    0.37
    quent
    0.36
    NewLine
    0.36
    反对
    0.35
    ્યા
    0.34
    䐈
    0.34
     доли
    0.34
    POSITIVE LOGITS
     es
    0.44
     esophagus
    0.43
     decorators
    0.42
    what
    0.41
    decorate
    0.41
     phosphatase
    0.40
     lanc
    0.39
     hari
    0.38
    WHAT
    0.38
     ES
    0.38
    Activations Density 0.000%

    No Known Activations