© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131599
    Prev
    Next
    INDEX
    Explanations

    Japón

    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_1_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
    /
    1.48
    ب
    1.36
    ه
    1.30
                
    1.28
    د
    1.28
    ,
    1.18
    в
    1.14
    a
    1.10
    ف
    1.08
    る
    1.06
    POSITIVE LOGITS
     l
    1.13
     peuple
    1.08
     süre
    1.02
     cette
    0.97
     quell
    0.94
    従って
    0.93
     mmol
    0.92
     هي
    0.91
     y
    0.91
    まれた
    0.90
    Activations Density 0.000%

    No Known Activations