© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5915
    Prev
    Next
    INDEX
    Explanations

    real money discussions

    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_40_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
    绔
    0.42
    㓡
    0.36
     الاكس
    0.35
    শায়
    0.34
     Reli
    0.34
    鐗
    0.34
    മിന്റെ
    0.34
    াগর
    0.32
    製
    0.32
    istiche
    0.32
    POSITIVE LOGITS
     real
    2.28
    real
    2.09
     реа
    2.03
    Real
    1.98
     Real
    1.88
    实
    1.81
     रियल
    1.76
    REAL
    1.73
     REAL
    1.70
    実
    1.56
    Activations Density 0.053%

    No Known Activations