© 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. 29861
    Prev
    Next
    INDEX
    Explanations

    qualities and states

    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_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
    y
    0.64
     và
    0.57
     and
    0.54
     And
    0.54
     also
    0.54
     এবং
    0.52
    kowo
    0.52
     также
    0.51
    s
    0.50
     Also
    0.49
    POSITIVE LOGITS
    ة
    0.46
     fournisseur
    0.44
    ել
    0.43
     taxon
    0.42
    وف
    0.41
    от
    0.41
     swarm
    0.41
     kanker
    0.40
    ون
    0.40
    որ
    0.40
    Activations Density 0.121%

    No Known Activations