© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180212
    Prev
    Next
    INDEX
    Explanations

    citing findings court rulings

    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_24_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
     viime
    0.35
    ICO
    0.33
     dernière
    0.32
     (°
    0.32
     terakhir
    0.32
     Raven
    0.31
     पुनः
    0.31
     દૂર
    0.31
    
    0.31
     CRE
    0.31
    POSITIVE LOGITS
     ذلك
    0.37
     thoſe
    0.35
     тази
    0.35
     această
    0.34
     reality
    0.33
    tabPadding
    0.33
    this
    0.33
     هذا
    0.33
     resize
    0.33
    ካከል
    0.32
    Activations Density 0.000%

    No Known Activations