© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3377
    Prev
    Next
    INDEX
    Explanations

    web ui, socket, port, api

    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
     MD
    0.47
    urig
    0.43
    读
    0.41
     README
    0.40
     JPG
    0.40
    MD
    0.39
     อ่าน
    0.39
     HPV
    0.38
     reading
    0.38
     읽
    0.38
    POSITIVE LOGITS
     фрон
    0.43
     api
    0.40
    フロント
    0.40
     फ्रंट
    0.39
    apy
    0.39
    frontend
    0.38
    Energy
    0.38
    api
    0.37
     ఫి
    0.37
    Geometry
    0.36
    Activations Density 0.268%

    No Known Activations