© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36151
    Prev
    Next
    INDEX
    Explanations

    display:

    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_11_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
    textColor
    0.28
    reliant
    0.28
     exig
    0.26
    getColor
    0.25
    walten
    0.25
    addColor
    0.25
    arci
    0.25
    ൻ
    0.25
     metas
    0.25
    Farland
    0.24
    POSITIVE LOGITS
    da
    0.32
    _
    0.31
    dinger
    0.28
     प्रधानमंत्री
    0.27
    de
    0.27
    mi
    0.26
     பிரதமர்
    0.26
    ↵↵↵
    0.26
     પ્રથમ
    0.26
    db
    0.26
    Activations Density 0.025%

    No Known Activations