© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27284
    Prev
    Next
    INDEX
    Explanations

    backpack

    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_10_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
    .
    1.01
    isca
    0.83
    "
    0.83
    í
    0.81
    iska
    0.77
    *
    0.76
    ί
    0.75
    아
    0.75
    <0x0D>
    0.75
    {
    0.74
    POSITIVE LOGITS
     背
    0.86
     Back
    0.85
     Backpack
    0.80
     Dover
    0.79
     BACK
    0.78
     Rücken
    0.77
    腧
    0.75
     Peut
    0.74
     U
    0.74
    ו
    0.70
    Activations Density 0.021%

    No Known Activations