© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11957
    Prev
    Next
    INDEX
    Explanations

    read, hear, encounter

    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_40_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
    కొ
    0.36
    erweise
    0.35
    క్కు
    0.34
    AMPLE
    0.33
     {:.
    0.33
    ুজ
    0.33
     तन
    0.33
    ោះ
    0.32
     HttpSession
    0.32
     വിശ്വാ
    0.32
    POSITIVE LOGITS
     read
    2.27
    read
    1.91
     읽
    1.85
     đọc
    1.79
     reads
    1.77
    อ่าน
    1.77
    读
    1.77
     Read
    1.74
    Read
    1.71
     reading
    1.70
    Activations Density 0.116%

    No Known Activations