© 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. 44865
    Prev
    Next
    INDEX
    Explanations

    cruise port and fjord

    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
    $
    0.60
     digit
    0.54
     locatie
    0.54
    seven
    0.52
     correção
    0.51
    But
    0.50
    Comme
    0.50
     ponsel
    0.50
    t
    0.50
    Digit
    0.49
    POSITIVE LOGITS
     meandering
    0.52
     cruisers
    0.50
     ವಿವಿಧ
    0.49
     departments
    0.48
    してきた
    0.48
    哳
    0.47
    出品
    0.46
    ରେ
    0.46
     수행
    0.46
    ́c
    0.45
    Activations Density 0.004%

    No Known Activations