© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235824
    Prev
    Next
    INDEX
    Explanations

    p

    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_46_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
    oprene
    0.40
    fetch
    0.40
    uruhan
    0.40
    צרים
    0.39
    鎿
    0.38
     moelle
    0.38
     modifier
    0.37
    نش
    0.37
     SRS
    0.37
    ინი
    0.37
    POSITIVE LOGITS
    hai
    0.39
    txt
    0.39
    AMP
    0.36
     విజయ
    0.35
    ลีก
    0.35
    ன்ஸ்
    0.35
     txt
    0.34
    徑
    0.34
    Lawrence
    0.34
    Hitpoint
    0.34
    Activations Density 0.001%

    No Known Activations