© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48656
    Prev
    Next
    INDEX
    Explanations

    html/css element selectors

    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_31_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
     Dest
    0.26
     ম্যাক
    0.26
     चलिए
    0.25
    >/</
    0.25
     Patten
    0.24
     北
    0.23
    Nord
    0.23
    _^
    0.23
     Nord
    0.23
    ^{*}$-
    0.23
    POSITIVE LOGITS
    nnet
    0.27
    nets
    0.27
     adjustments
    0.26
    cts
    0.26
     scorers
    0.26
     wach
    0.26
     hierarchical
    0.26
     pairwise
    0.26
     premieres
    0.26
    挝
    0.26
    Activations Density 0.004%

    No Known Activations