© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102252
    Prev
    Next
    INDEX
    Explanations

    watch

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    滕
    0.42
     Hinweise
    0.40
    phenoxy
    0.39
     ين
    0.39
     Hinweis
    0.38
     उर्वर
    0.38
     Pinch
    0.37
     Rode
    0.36
     Tennessee
    0.36
     References
    0.35
    POSITIVE LOGITS
    ㄏ
    0.39
    க்கப்பட்டது
    0.38
    新作
    0.38
     ಅಂತ
    0.38
    нал
    0.38
    ಟ್‌
    0.38
     καλύτε
    0.37
     কণ্
    0.36
     القناه
    0.36
     kualitas
    0.36
    Activations Density 0.001%

    No Known Activations