© 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. 29974
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    us
    0.80
    த்தகைய
    0.73
    ка
    0.70
    ј
    0.70
    ные
    0.67
     and
    0.65
    ाइवेट
    0.65
     questa
    0.65
    ન
    0.61
    <0x9C>
    0.61
    POSITIVE LOGITS
     demur
    0.81
    Loksatta
    0.77
     antiserum
    0.73
     oppon
    0.72
     extruder
    0.71
     تقل
    0.71
     नया
    0.70
     并
    0.70
     enteral
    0.70
    MQTT
    0.70
    Activations Density 0.000%

    No Known Activations