© 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. 162717
    Prev
    Next
    INDEX
    Explanations

    baking ingredients and amounts

    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
    投资
    0.40
    ాలకు
    0.39
     california
    0.39
    구
    0.39
     migratory
    0.38
     California
    0.37
     CALIFORNIA
    0.37
     प्रवासी
    0.37
    hæng
    0.37
     hydraul
    0.37
    POSITIVE LOGITS
    獾
    0.39
     mik
    0.38
    ◌
    0.37
     le
    0.35
     ファン
    0.35
     требо
    0.35
     drowned
    0.34
     Fairy
    0.34
     Зна
    0.34
    Ally
    0.34
    Activations Density 0.007%

    No Known Activations