© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129085
    Prev
    Next
    INDEX
    Explanations

    inhalation / halothane

    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_1_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
     is
    1.34
    Rs
    1.23
    electric
    1.13
    alto
    1.06
    star
    1.02
     a
    1.01
    ार
    1.00
    SO
    0.98
    S
    0.97
    IK
    0.97
    POSITIVE LOGITS
    在
    1.33
    é
    1.29
    ও
    1.29
    '
    1.14
    も
    1.09
    ने
    1.07
    у
    1.07
     antica
    1.02
     requis
    1.01
    to
    1.00
    Activations Density 0.001%

    No Known Activations