© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206174
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    rawData
    0.46
     sollten
    0.42
    ഈ
    0.41
     när
    0.41
    ambulance
    0.41
     useNavigate
    0.40
    ваны
    0.39
     allait
    0.39
     wanneer
    0.39
     Holding
    0.39
    POSITIVE LOGITS
     conjugation
    0.36
     प्रश
    0.35
     ਉਸ
    0.35
    势力
    0.34
    ﺲ
    0.34
    hiqdev
    0.33
     scriptlevel
    0.33
     lad
    0.33
    糕
    0.33
     sportsman
    0.32
    Activations Density 0.000%

    No Known Activations