© 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. 202671
    Prev
    Next
    INDEX
    Explanations

    dice rolls

    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
     восем
    0.46
     oss
    0.43
    six
    0.39
    
    0.38
    eight
    0.38
    getSize
    0.38
    pageSize
    0.38
    ото
    0.37
    Chevrolet
    0.37
    inert
    0.36
    POSITIVE LOGITS
     tempt
    0.39
     බ
    0.39
     फिल
    0.39
     kettle
    0.39
    fov
    0.37
     አንድ
    0.36
     lay
    0.36
     Doct
    0.35
    玻
    0.35
     tempted
    0.35
    Activations Density 0.003%

    No Known Activations