© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44907
    Prev
    Next
    INDEX
    Explanations

    emoticons or punctuation

    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_13_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
    e
    0.64
     last
    0.57
     Lawyer
    0.57
    et
    0.52
    最
    0.52
     board
    0.50
    data
    0.49
    last
    0.48
    Board
    0.48
     call
    0.48
    POSITIVE LOGITS
     Usuarios
    0.65
     Produtos
    0.61
     Wikiped
    0.59
     receptacles
    0.59
     Pubmed
    0.56
    ਕ
    0.56
    UIActions
    0.55
     Refunds
    0.54
     queremos
    0.53
     mesmos
    0.53
    Activations Density 0.000%

    No Known Activations