© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38276
    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_11_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
    terus
    0.53
     راجس
    0.50
    Uuid
    0.46
    InRange
    0.46
     ट्रांस
    0.46
    aigne
    0.46
    TERY
    0.46
    ন
    0.46
    تام
    0.45
    etable
    0.45
    POSITIVE LOGITS
    ری
    0.59
     joke
    0.52
     visit
    0.50
     historian
    0.50
     lady
    0.50
     spok
    0.50
     propos
    0.49
     Joke
    0.47
     landsc
    0.47
     playwright
    0.46
    Activations Density 0.000%

    No Known Activations