© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80001
    Prev
    Next
    INDEX
    Explanations

    try, experiment, test

    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
     documentos
    0.41
     suunn
    0.39
    documents
    0.38
    canada
    0.37
     اللجنة
    0.36
    捃
    0.36
     документов
    0.36
     कंधे
    0.35
    telephone
    0.35
    }/\
    0.35
    POSITIVE LOGITS
    Experiment
    0.50
     experiment
    0.48
    試し
    0.45
     Experiment
    0.44
    实验
    0.42
     experimenting
    0.42
     experiments
    0.42
    Retry
    0.42
    试
    0.41
     tested
    0.41
    Activations Density 0.050%

    No Known Activations