© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15196
    Prev
    Next
    INDEX
    Explanations

    foreach loops

    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_13_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
    包括
    0.63
     wavenumber
    0.57
    𝙨
    0.57
    形態
    0.56
    علم
    0.54
    아버지
    0.53
    微微
    0.52
     h
    0.52
    流动
    0.52
    𢎞
    0.52
    POSITIVE LOGITS
    v
    0.62
    -
    0.61
    otts
    0.58
    »)
    0.57
    kek
    0.55
    j
    0.55
    ))
    0.55
    u
    0.54
    ä
    0.54
    ocon
    0.54
    Activations Density 0.007%

    No Known Activations