© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99481
    Prev
    Next
    INDEX
    Explanations

    stratified splitting and sampling

    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_14_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
     wypad
    0.52
    agamanam
    0.50
     ଓ
    0.49
     plasmas
    0.49
     無料
    0.49
    нт
    0.48
     අතර
    0.48
    ellular
    0.46
    यॉर्क
    0.46
     عصر
    0.46
    POSITIVE LOGITS
    hen
    0.56
    ren
    0.54
    |
    0.53
    chen
    0.51
     বা
    0.49
    šk
    0.49
     to
    0.49
    this
    0.48
     c
    0.48
    /]
    0.48
    Activations Density 0.000%

    No Known Activations