© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35933
    Prev
    Next
    INDEX
    Explanations

    places

    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_7_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
     xylem
    0.37
    ين
    0.37
    كا
    0.36
     at
    0.35
    鎶
    0.35
     mieć
    0.35
     externalities
    0.35
     axons
    0.35
     terület
    0.35
     scaffolds
    0.35
    POSITIVE LOGITS
    ↵↵
    0.49
    ring
    0.46
    time
    0.45
    day
    0.45
    for
    0.42
    not
    0.41
    ol
    0.41
    ite
    0.41
    we
    0.40
    ric
    0.40
    Activations Density 0.018%

    No Known Activations