© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122522
    Prev
    Next
    INDEX
    Explanations

    subject seeing or noticing

    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_38_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
     تكون
    0.42
     midst
    0.41
    counterx
    0.41
    监测
    0.39
    셧
    0.39
     været
    0.39
    쩡
    0.39
     intimid
    0.38
    divider
    0.38
     соль
    0.38
    POSITIVE LOGITS
     judged
    0.44
     ase
    0.41
     here
    0.38
     здесь
    0.38
    様の
    0.37
     heard
    0.36
     F
    0.36
    accharides
    0.36
    íveis
    0.36
    ݨ
    0.35
    Activations Density 0.003%

    No Known Activations