© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148530
    Prev
    Next
    INDEX
    Explanations

    Practical

    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_59_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
     cap
    0.50
    cap
    0.50
    П
    0.43
    エイ
    0.42
    Π
    0.42
    There
    0.40
    キャップ
    0.40
    ETH
    0.40
    Cap
    0.38
    Programs
    0.37
    POSITIVE LOGITS
     Example
    0.50
     Side
    0.50
     Old
    0.49
    ແລະ
    0.46
     والمع
    0.45
     Most
    0.45
     Record
    0.44
     v
    0.44
     Considered
    0.44
     Opened
    0.43
    Activations Density 0.002%

    No Known Activations