© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100528
    Prev
    Next
    INDEX
    Explanations

    capacitance, dryness, or bloating

    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_14_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
     assures
    0.50
     다
    0.50
     jaanu
    0.50
    ாளையம்
    0.49
     Ensures
    0.49
     ooz
    0.48
     asegurarse
    0.48
     cracks
    0.47
     reassured
    0.46
     assurent
    0.46
    POSITIVE LOGITS
    Rd
    0.57
     vendido
    0.53
    Ῥ
    0.53
    넵
    0.52
    轂
    0.52
    CS
    0.51
    Road
    0.50
    Beijing
    0.49
    規則
    0.49
     विक्री
    0.49
    Activations Density 0.028%

    No Known Activations