© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106757
    Prev
    Next
    INDEX
    Explanations

    ca followed by 'usal'

    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
    d
    1.30
    д
    1.11
    lad
    1.05
    s
    1.04
    g
    0.98
    স
    0.95
    mp
    0.95
    st
    0.92
    locks
    0.90
    ak
    0.88
    POSITIVE LOGITS
     execut
    1.17
    {
    1.16
     caffè
    1.10
    _
    1.10
     peut
    1.05
     uporab
    1.04
    あります
    1.02
     estará
    1.02
     końcu
    1.02
     iunie
    1.02
    Activations Density 0.001%

    No Known Activations