© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 199080
    Prev
    Next
    INDEX
    Explanations

    Mendy, Mendix, Mandiant, mediant

    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_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ى
    1.15
    。</
    1.01
    ве
    1.00
    ）。
    0.99
    。
    0.98
    вени
    0.95
    ра
    0.93
    ால்
    0.91
    <0x80>
    0.90
    та
    0.89
    POSITIVE LOGITS
    p
    1.41
    t
    1.30
    es
    1.29
    n
    1.25
    d
    1.12
    :
    1.12
    x
    1.09
    MP
    1.05
    k
    1.03
    ent
    1.02
    Activations Density 0.000%

    No Known Activations