© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84108
    Prev
    Next
    INDEX
    Explanations

    web scraping

    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_23_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
    สู
    0.38
    ^*(\
    0.36
    śred
    0.36
     været
    0.36
    ayam
    0.35
    èce
    0.35
    出手
    0.35
    oxy
    0.34
    iser
    0.34
     فيلم
    0.34
    POSITIVE LOGITS
     appropriateness
    0.39
    рун
    0.35
    笅
    0.35
     aigus
    0.33
    PURE
    0.33
    ngthening
    0.33
     коли
    0.33
     நாள
    0.33
     discos
    0.32
     জিয়া
    0.32
    Activations Density 0.012%

    No Known Activations