© 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. 68885
    Prev
    Next
    INDEX
    Explanations

    wearing clothes

    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
    猬
    0.39
     independência
    0.38
    INFIN
    0.37
     बाघ
    0.36
    fasta
    0.36
    panda
    0.35
     infin
    0.35
     Wait
    0.35
     डॉट
    0.35
    aw
    0.34
    POSITIVE LOGITS
     fora
    0.43
     eile
    0.42
    暇
    0.39
     clothe
    0.38
     sweaters
    0.38
    PlayerSelector
    0.38
     sweater
    0.38
     stoichi
    0.38
    Out
    0.37
    colorize
    0.37
    Activations Density 0.012%

    No Known Activations