© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140529
    Prev
    Next
    INDEX
    Explanations

    evaluate sourcing

    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_46_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
    玑
    0.46
     ingeniero
    0.42
    托
    0.41
    蟳
    0.40
     lawyer
    0.39
    Events
    0.39
    ridos
    0.39
    மையும்
    0.39
    idades
    0.38
     Mart
    0.38
    POSITIVE LOGITS
     sourcing
    0.54
     sourced
    0.49
     deal
    0.48
     évaluation
    0.46
     evaluation
    0.44
    육
    0.43
    ourced
    0.42
     evaluating
    0.42
    評価
    0.42
     evaluate
    0.41
    Activations Density 0.001%

    No Known Activations