© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18543
    Prev
    Next
    INDEX
    Explanations

    user names and associated content

    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_34_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
    我的
    0.36
    加速度
    0.36
    ,-
    0.36
    scriptstyle
    0.34
    RICT
    0.34
     meus
    0.34
     సాహిత్య
    0.34
    стива
    0.33
    tabname
    0.33
    :"",
    0.33
    POSITIVE LOGITS
     ইয়াহিয়া
    0.43
     갖
    0.40
     psychology
    0.39
     aging
    0.39
    ಾಯ
    0.38
     मिळाली
    0.38
     स्थापित
    0.38
     Cary
    0.38
    とも
    0.38
     DIGITAL
    0.38
    Activations Density 0.001%

    No Known Activations