© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158851
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    igos
    0.40
    vm
    0.38
    kim
    0.37
     गुरू
    0.37
    chemic
    0.37
    arity
    0.36
    耆
    0.36
    깝
    0.35
     दे
    0.35
    গী
    0.35
    POSITIVE LOGITS
     nutrition
    0.40
     Nutrition
    0.38
    Nutrition
    0.37
     Rob
    0.37
     whitew
    0.34
     Rubber
    0.34
    ຕ່
    0.34
     অ্যাস
    0.33
     nutric
    0.33
    🧴
    0.33
    Activations Density 0.002%

    No Known Activations