© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 51051
    Prev
    Next
    INDEX
    Explanations

    practical and actionable advice

    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
     δεύτε
    0.38
    Mort
    0.36
    顼
    0.36
     მს
    0.32
     bölümde
    0.32
     Mort
    0.32
    endorf
    0.32
    澡
    0.31
     pierwszym
    0.31
     परीक्षाओं
    0.31
    POSITIVE LOGITS
     logic
    0.37
     revolution
    0.37
     usher
    0.36
     cord
    0.35
     mainly
    0.34
     பணி
    0.34
     soluciones
    0.34
     plain
    0.32
     sheer
    0.32
     Clothes
    0.32
    Activations Density 0.022%

    No Known Activations