© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68497
    Prev
    Next
    INDEX
    Explanations

    print

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    膊
    0.37
     sw
    0.35
    Nam
    0.35
     Drainage
    0.35
    sw
    0.34
    Statement
    0.34
    ungsver
    0.33
    tenance
    0.33
     विधेयक
    0.33
    technik
    0.33
    POSITIVE LOGITS
     Something
    0.42
     Furious
    0.37
     reviewing
    0.36
    勇
    0.36
     adjud
    0.36
     ஏற்பட்ட
    0.36
     sufrió
    0.36
     வெப்சீரி
    0.36
     something
    0.35
     severe
    0.35
    Activations Density 0.006%

    No Known Activations