© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234630
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     Rye
    1.12
     rye
    1.07
     barley
    1.00
     Barley
    0.93
     spelt
    0.76
    麦
    0.76
     Malt
    0.75
     malt
    0.74
    麥
    0.74
     spelled
    0.71
    POSITIVE LOGITS
    פי
    0.39
    Dot
    0.39
    旋转
    0.38
    unist
    0.38
    thia
    0.37
    Hij
    0.37
    括号
    0.37
    entiti
    0.37
    િલ
    0.36
     doulou
    0.36
    Activations Density 0.006%

    No Known Activations