© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220679
    Prev
    Next
    INDEX
    Explanations

    House of Representatives

    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_10_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
    is
    0.41
    یکن
    0.38
    assess
    0.37
    ᴅ
    0.37
     ನಗರ
    0.37
    ޘ
    0.36
    Ꮶ
    0.35
    SAT
    0.34
    ᱫ
    0.34
     राजधानी
    0.34
    POSITIVE LOGITS
    יות
    0.36
     flashy
    0.31
    я
    0.31
     on
    0.30
     fino
    0.30
     jang
    0.30
     trivial
    0.30
    ">)</
    0.30
    ducers
    0.30
    します
    0.29
    Activations Density 0.002%

    No Known Activations