© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17866
    Prev
    Next
    INDEX
    Explanations

    вращение or VR

    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
     صف
    0.44
     দেহের
    0.37
    ürm
    0.36
     הרב
    0.36
    ELDS
    0.36
     بدور
    0.36
    舍
    0.35
    ifera
    0.35
    腆
    0.35
    ፧
    0.34
    POSITIVE LOGITS
     mum
    0.36
     Subsidi
    0.36
    ógy
    0.35
     وسي
    0.35
    getic
    0.35
    Truck
    0.35
     strictly
    0.34
     proceeding
    0.34
     Davenport
    0.34
     ftp
    0.34
    Activations Density 0.016%

    No Known Activations