© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14949
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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_13_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
    ংলা
    0.50
     descriptive
    0.49
    ෲ
    0.48
     rockers
    0.48
     llam
    0.47
     assaulted
    0.46
     besch
    0.46
     lista
    0.46
     galleries
    0.45
     rp
    0.45
    POSITIVE LOGITS
    TR
    0.54
    comp
    0.54
    didn
    0.54
    Xia
    0.51
    double
    0.51
    P
    0.51
    C
    0.50
    water
    0.49
    Xinhua
    0.49
    tenth
    0.49
    Activations Density 0.000%

    No Known Activations