© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151521
    Prev
    Next
    INDEX
    Explanations

    headquartered or based in

    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_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    composed
    0.52
     AcOH
    0.49
     Iwas
    0.49
    CCCN
    0.47
     wonderland
    0.46
    ：
    0.46
     oxid
    0.46
    fte
    0.46
    isoft
    0.46
    BIUM
    0.46
    POSITIVE LOGITS
     rout
    0.53
     locations
    0.53
     siguiendo
    0.52
     nở
    0.47
     seguinte
    0.46
     onay
    0.46
     jump
    0.43
     размещения
    0.43
     estatura
    0.43
     ý
    0.42
    Activations Density 0.000%

    No Known Activations