© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57620
    Prev
    Next
    INDEX
    Explanations

    **mathematical function calls**

    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_11_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
    ”
    0.10
    ada
    0.09
     de
    0.09
     puede
    0.08
    ían
    0.08
    amenti
    0.08
    ate
    0.08
    \
    0.08
    amento
    0.08
    atrol
    0.08
    POSITIVE LOGITS
     인도
    0.11
     भारतात
    0.09
     Yath
    0.09
     Indien
    0.09
     आणि
    0.09
     미국
    0.09
    伌
    0.09
    eine
    0.09
     etiology
    0.09
    ットフォーム
    0.09
    Activations Density 0.003%

    No Known Activations