© 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. 201664
    Prev
    Next
    INDEX
    Explanations

    python function definitions

    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
    hus
    0.41
    賓
    0.40
     hus
    0.38
    擠
    0.37
    ತಿಯ
    0.37
     fund
    0.36
    勞
    0.36
    ATIV
    0.36
     противо
    0.35
     Fund
    0.35
    POSITIVE LOGITS
     ناخد
    0.45
    दिव
    0.41
    Levels
    0.41
    鿉
    0.39
    ويات
    0.37
     llevo
    0.37
    咾
    0.37
     carrying
    0.37
     exercising
    0.37
     llevando
    0.37
    Activations Density 0.001%

    No Known Activations