© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32304
    Prev
    Next
    INDEX
    Explanations

    places, organizations, or features

    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_40_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
     సే
    0.39
    양
    0.38
    に使用
    0.37
     Haf
    0.36
     dara
    0.36
    ीकरण
    0.36
    িরে
    0.35
    fake
    0.35
     fragrances
    0.35
     perfumes
    0.34
    POSITIVE LOGITS
     Accent
    0.37
    arian
    0.36
    Accent
    0.35
     प्रचलित
    0.35
     pipelines
    0.35
     -(
    0.35
     بعنوان
    0.35
    subtitle
    0.34
     Aviation
    0.34
     ác
    0.34
    Activations Density 0.011%

    No Known Activations