© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40140
    Prev
    Next
    INDEX
    Explanations

    time series database

    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_11_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
    τές
    0.54
     README
    0.49
    ση
    0.48
    赁
    0.47
    romagnet
    0.47
    sliding
    0.47
    фесси
    0.46
    тье
    0.46
    粱
    0.46
    τής
    0.45
    POSITIVE LOGITS
    abbit
    0.57
    un
    0.52
     erreichen
    0.49
    angent
    0.49
     حفاظت
    0.48
    gruppen
    0.47
     socketList
    0.47
    ards
    0.47
     helt
    0.46
    icke
    0.46
    Activations Density 0.000%

    No Known Activations