© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164559
    Prev
    Next
    INDEX
    Explanations

    load programs or materials

    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_31_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
     உண
    0.34
     err
    0.33
    dinitro
    0.32
    係
    0.31
     {|
    0.31
    ර්ග
    0.30
    டர்
    0.29
     குறிப்பிட
    0.29
    odeal
    0.29
    前面
    0.29
    POSITIVE LOGITS
    OfInterest
    0.35
     investigated
    0.31
     debugger
    0.31
     library
    0.31
     उछ
    0.31
    ivant
    0.30
    현
    0.30
     भूमि
    0.30
     corret
    0.30
     persone
    0.29
    Activations Density 0.002%

    No Known Activations