© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214187
    Prev
    Next
    INDEX
    Explanations

    organizations or actions

    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_50_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
    ווה
    0.50
    媧
    0.43
    стива
    0.41
     Generators
    0.39
     ಸು
    0.39
     राइ
    0.38
    qua
    0.37
    Generator
    0.37
    Upgradeable
    0.37
    拼接
    0.37
    POSITIVE LOGITS
    కొని
    0.41
     messen
    0.41
     Meso
    0.40
     Mesa
    0.39
    ୭
    0.39
     Glide
    0.38
     Strawberry
    0.37
     Andersen
    0.36
     Wick
    0.36
     Landmarks
    0.36
    Activations Density 0.007%

    No Known Activations