© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98118
    Prev
    Next
    INDEX
    Explanations

    effortless chic, cool, sophistication

    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_14_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
        
    0.66
    u
    0.63
    (
    0.62
    And
    0.57
         
    0.57
    w
    0.56
    Trans
    0.55
    New
    0.55
    र
    0.55
    !(
    0.55
    POSITIVE LOGITS
    선의
    0.52
    скольку
    0.51
    贵的
    0.51
    ముఖ
    0.51
     ಕ್ಷೇತ್ರ
    0.50
     அவர்களுடைய
    0.50
    hensible
    0.49
     능력
    0.48
     ரே
    0.48
    諌
    0.48
    Activations Density 0.000%

    No Known Activations