© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18009
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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_15_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
     ngunit
    0.10
     但是
    0.10
     뭐라고
    0.09
     ，
    0.09
     GoName
    0.09
    語
    0.09
     defaultConfig
    0.09
    色々
    0.09
     lineColor
    0.09
     coração
    0.09
    POSITIVE LOGITS
    so
    0.16
    for
    0.15
    an
    0.14
    this
    0.12
    j
    0.12
    ord
    0.12
    organiz
    0.12
     for
    0.11
    jit
    0.11
    oh
    0.11
    Activations Density 0.024%

    No Known Activations