© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132076
    Prev
    Next
    INDEX
    Explanations

    healthcare delivery

    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
    :
    1.42
    ()
    1.20
    I
    1.20
    1.16
     inoxidable
    1.02
    锟
    1.02
    <0xF3>
    1.00
    In
    0.98
    :”
    0.98
    П
    0.98
    POSITIVE LOGITS
    ang
    1.30
    ut
    1.21
    ir
    1.10
    n
    1.10
    t
    1.00
    ुर
    0.97
    k
    0.96
    ars
    0.96
    ک
    0.95
    ri
    0.95
    Activations Density 0.002%

    No Known Activations