© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179974
    Prev
    Next
    INDEX
    Explanations

    Pythagorean theorem

    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_29_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
    合理的
    0.40
     正
    0.38
     gx
    0.38
    compassing
    0.38
     obowiąz
    0.37
     പ്രദേശ
    0.37
    真实的
    0.37
    出来的
    0.36
    रियो
    0.36
    骇
    0.36
    POSITIVE LOGITS
    าลัย
    0.37
     Webseite
    0.37
    durch
    0.37
     descont
    0.37
    不必
    0.36
    lily
    0.36
    oxyde
    0.36
     alcalde
    0.36
     kalem
    0.35
     الب
    0.35
    Activations Density 0.001%

    No Known Activations