© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205326
    Prev
    Next
    INDEX
    Explanations

    equation markers and structure

    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_37_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
     und
    0.40
    Tokens
    0.40
     antibodies
    0.38
     asymmetric
    0.38
    Compare
    0.38
     compare
    0.37
    (";
    0.37
     Your
    0.37
     antioxidant
    0.37
    assertThat
    0.37
    POSITIVE LOGITS
    时长
    0.40
    哉
    0.39
    ورو
    0.39
    STRACT
    0.39
     Title
    0.38
    了我
    0.38
    赛季
    0.36
    Title
    0.36
     Eq
    0.35
     час
    0.35
    Activations Density 0.001%

    No Known Activations