© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193559
    Prev
    Next
    INDEX
    Explanations

    security, vulnerability, communication especially listening

    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_9_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
    as
    0.48
    an
    0.48
    ވަ
    0.46
    หลัก
    0.46
    夶
    0.45
     במהלך
    0.45
    Під
    0.45
     Prins
    0.45
    ó
    0.44
    یس
    0.44
    POSITIVE LOGITS
     immobil
    0.52
     knowingly
    0.52
     consultez
    0.52
     outra
    0.51
     poda
    0.51
     nadie
    0.50
     lick
    0.49
     kan
    0.49
     tell
    0.49
     depict
    0.49
    Activations Density 0.000%

    No Known Activations