© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145799
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     cellulosic
    0.48
    .+
    0.43
     prosecutors
    0.41
     shutil
    0.41
     stroller
    0.39
     onslaught
    0.39
     fairway
    0.39
     ashore
    0.39
    SetFloat
    0.38
     potatoes
    0.38
    POSITIVE LOGITS
    that
    0.46
    子上
    0.44
    this
    0.43
    for
    0.43
    providing
    0.42
    ęcia
    0.41
    _',
    0.41
    ২
    0.40
    being
    0.38
    including
    0.38
    Activations Density 0.001%

    No Known Activations