© 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. 6122
    Prev
    Next
    INDEX
    Explanations

    junit tests

    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
     Auro
    0.40
     الفور
    0.39
    钿
    0.39
     আশ্চর্য
    0.39
    柊
    0.39
    chutz
    0.39
     sostenibilidad
    0.39
    ="../../
    0.38
    味わ
    0.37
     continuidad
    0.37
    POSITIVE LOGITS
     expansions
    0.36
     though
    0.36
    ivamente
    0.36
     depend
    0.36
    నాల
    0.36
     ধারনা
    0.36
     condens
    0.35
     leasing
    0.35
     vip
    0.35
     جنا
    0.35
    Activations Density 0.001%

    No Known Activations