© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207019
    Prev
    Next
    INDEX
    Explanations

    Price-to-Book ratio

    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_20_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
    /
    0.54
     અને
    0.52
     Min
    0.52
     Cal
    0.50
     و
    0.49
     ও
    0.49
     Condition
    0.49
     Clyde
    0.48
     &
    0.48
     và
    0.47
    POSITIVE LOGITS
    ਵਾਈ
    0.46
    ONTAL
    0.46
    벅
    0.45
     antitumor
    0.45
    Datasets
    0.45
     erkannt
    0.44
    ўнай
    0.44
    prestations
    0.44
    ContactBundle
    0.43
    Ronald
    0.42
    Activations Density 0.001%

    No Known Activations