© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89101
    Prev
    Next
    INDEX
    Explanations

    algo modifying adjectives/descriptions

    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_11_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
    ra
    0.68
    reta
    0.64
    원의
    0.63
    ри
    0.63
     ಯಾವಾಗ
    0.63
     ಯಾವುದ
    0.62
     ವರ್
    0.61
    ቝ
    0.60
    ພວກເຮົາ
    0.60
    ku
    0.59
    POSITIVE LOGITS
     prueba
    0.62
    (
    0.58
     sist
    0.55
    ส
    0.54
     It
    0.52
     borde
    0.52
    ↵
    0.52
     cambio
    0.51
     volte
    0.50
     spider
    0.50
    Activations Density 0.001%

    No Known Activations