© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16580
    Prev
    Next
    INDEX
    Explanations

    Steam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
     sh
    0.50
    тельство
    0.50
     Award
    0.49
     Toggle
    0.48
     CHARSET
    0.48
    渝
    0.48
     HBase
    0.48
     Query
    0.47
    Browsable
    0.46
     Array
    0.46
    POSITIVE LOGITS
    貓
    0.53
    Plastic
    0.52
    ानी
    0.50
    ଗ
    0.50
    arına
    0.48
    ఠ
    0.48
     فال
    0.48
    きましたが
    0.47
     खेल
    0.46
     وو
    0.46
    Activations Density 0.007%

    No Known Activations