© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121448
    Prev
    Next
    INDEX
    Explanations

    incubation or intubation

    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_3_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
    ری
    0.63
    д
    0.63
    не
    0.62
    онов
    0.62
    т
    0.60
    ை
    0.59
    𝐭
    0.59
    н
    0.59
    ле
    0.58
     precession
    0.58
    POSITIVE LOGITS
     a
    0.98
     de
    0.79
    1
    0.73
    \
    0.71
    (
    0.70
    Spe
    0.68
    L
    0.68
    Sos
    0.67
    Cons
    0.66
    Tor
    0.66
    Activations Density 0.001%

    No Known Activations