© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54158
    Prev
    Next
    INDEX
    Explanations

    circumflex words for yoga

    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_31_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
     widely
    0.36
    ittha
    0.36
    rivate
    0.35
    副本
    0.33
     Baud
    0.33
    REGISTER
    0.33
     LANGUAGES
    0.33
     ம
    0.32
     හැකි
    0.32
    omotive
    0.32
    POSITIVE LOGITS
     rosé
    0.43
    ή
    0.40
     differences
    0.39
     traction
    0.39
     résoudre
    0.38
     anton
    0.38
     distinguir
    0.37
    𝔂
    0.37
     Roz
    0.37
     pras
    0.37
    Activations Density 0.007%

    No Known Activations