© 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
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 195548
    Prev
    Next
    INDEX
    Explanations

    "Constraints" context

    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_26_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
     Northumberland
    0.37
    <eos>
    0.36
    Worker
    0.35
    ্ঠ
    0.35
    peaks
    0.35
     Gloucester
    0.34
     Acerca
    0.34
    новременно
    0.34
    Indexer
    0.33
    nt
    0.33
    POSITIVE LOGITS
    ହା
    0.45
     විශ්
    0.42
     empe
    0.41
     자신이
    0.41
     смя
    0.41
    ᵇ
    0.40
    Ֆ
    0.40
     aseg
    0.39
     Behandlung
    0.39
     chuyện
    0.39
    Activations Density 0.000%

    No Known Activations