© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9462
    Prev
    Next
    INDEX
    Explanations

    titles and City

    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_13_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
    стям
    0.61
     कनेक्टिव
    0.59
    thew
    0.59
    putes
    0.59
    𝘀
    0.59
    pekt
    0.58
    iszt
    0.56
    alev
    0.55
    <unused988>
    0.55
    anele
    0.55
    POSITIVE LOGITS
     desn
    0.49
     rooftops
    0.48
     въз
    0.47
    {
    0.46
     بن
    0.45
    for
    0.45
     nore
    0.44
     roof
    0.44
     bare
    0.44
     Bare
    0.44
    Activations Density 0.014%

    No Known Activations