© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30502
    Prev
    Next
    INDEX
    Explanations

    surrounded by or surrounding context

    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
    Negative Logits
     and
    0.35
    ك
    0.29
     o
    0.28
    ği
    0.28
    ı
    0.28
     você
    0.28
    يث
    0.28
     и
    0.27
     vous
    0.27
     ecz
    0.27
    POSITIVE LOGITS
    s
    0.35
    b
    0.29
    Been
    0.29
    u
    0.28
    p
    0.28
    v
    0.28
    z
    0.27
    sud
    0.26
    sda
    0.26
    t
    0.26
    Activations Density 0.006%

    No Known Activations