© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208962
    Prev
    Next
    INDEX
    Explanations

    Face

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    numpy
    0.43
    pytest
    0.41
    gae
    0.39
    Py
    0.38
    ('')
    0.38
    ార్క్
    0.38
    ={}
    0.37
    Anne
    0.37
    matplotlib
    0.37
    ారం
    0.37
    POSITIVE LOGITS
    光
    0.57
     光
    0.46
     quang
    0.42
     ecos
    0.40
     star
    0.39
    sky
    0.38
     disability
    0.38
     optical
    0.38
     aeronaut
    0.37
     eco
    0.36
    Activations Density 0.001%

    No Known Activations