© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1567
    Prev
    Next
    INDEX
    Explanations

    Google search URLs

    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_39_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
    реди
    0.27
    CAPT
    0.27
     meg
    0.27
    顼
    0.26
    ياً
    0.26
    sonar
    0.26
    ografico
    0.26
     Capt
    0.26
    閔
    0.26
    प्त
    0.26
    POSITIVE LOGITS
     جلد
    0.31
     straighten
    0.31
     linda
    0.30
     leaner
    0.30
     healthier
    0.29
    حد
    0.27
     skinny
    0.27
     prettiest
    0.27
     жидко
    0.26
     sehat
    0.26
    Activations Density 0.008%

    No Known Activations