© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88689
    Prev
    Next
    INDEX
    Explanations

    Leibniz, Wolff, Romantic, Friedrich, fragmentation

    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_11_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
     et
    0.55
    phi
    0.55
     direita
    0.53
     biais
    0.51
    ’
    0.51
     Grand
    0.51
     at
    0.50
    fraction
    0.50
     át
    0.50
     ponto
    0.50
    POSITIVE LOGITS
    ABA
    0.53
    agun
    0.49
    ጠና
    0.48
     Schall
    0.48
    Measured
    0.48
    (||
    0.48
    тку
    0.47
    (\|
    0.47
     angesehen
    0.47
    тков
    0.46
    Activations Density 0.016%

    No Known Activations