© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 164611
    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_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
     TREATMENT
    0.41
    蘄
    0.40
    圆形
    0.40
    يون
    0.39
     महामारी
    0.39
     கவு
    0.39
    EMA
    0.38
    Meta
    0.38
     caravans
    0.38
     Zentr
    0.37
    POSITIVE LOGITS
     dish
    0.39
     fortitude
    0.37
     रफी
    0.37
     Grayson
    0.36
     sued
    0.35
     references
    0.34
    蕗
    0.34
     دستی
    0.34
     convincing
    0.33
    alaya
    0.33
    Activations Density 0.000%

    No Known Activations