© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96658
    Prev
    Next
    INDEX
    Explanations

    modulation, regulation, voltage, phase, saturation

    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
     ఫలి
    0.56
    льд
    0.52
     पुष्पा
    0.52
    䏲
    0.52
     инсу
    0.50
     لوب
    0.49
     "...
    0.49
     दिव
    0.48
     እር
    0.48
     meriye
    0.48
    POSITIVE LOGITS
     Col
    0.52
    tx
    0.49
     b
    0.48
     B
    0.46
     V
    0.45
     basic
    0.45
    ey
    0.45
     Hol
    0.45
    娘
    0.45
    ī
    0.44
    Activations Density 0.022%

    No Known Activations