© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75459
    Prev
    Next
    INDEX
    Explanations

    binance

    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
     signal
    0.40
     oars
    0.39
     breeding
    0.36
     ورځې
    0.36
    ٹنگ
    0.36
     strides
    0.35
    ActionEvent
    0.35
    公
    0.35
     opportunity
    0.34
     asseg
    0.34
    POSITIVE LOGITS
    抔
    0.36
    Radiux
    0.35
    最小
    0.35
     samod
    0.35
    节日
    0.35
     развитии
    0.35
    Pf
    0.35
    Offers
    0.34
    Lowest
    0.33
    最
    0.33
    Activations Density 0.001%

    No Known Activations