© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103146
    Prev
    Next
    INDEX
    Explanations

    numbers followed by colons

    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_1_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
     a
    1.34
    ação
    1.17
     và
    1.05
    of
    1.02
     of
    1.00
    am
    1.00
     have
    0.93
     dịch
    0.93
     و
    0.91
     phần
    0.91
    POSITIVE LOGITS
    y
    1.20
    ش
    1.00
    quele
    0.95
    써
    0.93
    де
    0.91
    പ
    0.91
    د
    0.88
     Comunic
    0.87
    끔
    0.86
    x
    0.84
    Activations Density 0.005%

    No Known Activations