© 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. 54228
    Prev
    Next
    INDEX
    Explanations

    mathematics and physics concepts

    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
     odont
    0.43
     boxing
    0.41
    ษัท
    0.40
     extract
    0.40
     ದಾ
    0.40
     በእ
    0.39
    ੫
    0.39
    Boxing
    0.38
     extracting
    0.37
    竭
    0.37
    POSITIVE LOGITS
     Funktion
    0.34
    considered
    0.33
     töö
    0.33
    characterized
    0.33
     mater
    0.33
     অর্ধ
    0.33
    νή
    0.33
    šu
    0.32
    筠
    0.32
     Prong
    0.32
    Activations Density 0.001%

    No Known Activations