© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217728
    Prev
    Next
    INDEX
    Explanations

    rare or unusual things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     Cun
    0.38
     sdl
    0.38
     thể
    0.37
     존
    0.37
     tds
    0.37
    снаб
    0.37
     PROTO
    0.37
     TDS
    0.37
    霑
    0.37
     protocol
    0.36
    POSITIVE LOGITS
     rare
    0.86
    rare
    0.86
     rarely
    0.85
    Rare
    0.82
     Rare
    0.79
     दुर्लभ
    0.78
     selten
    0.75
     seldom
    0.75
     rarer
    0.75
     rares
    0.74
    Activations Density 0.044%

    No Known Activations