© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7953
    Prev
    Next
    INDEX
    Explanations

    asking what do you think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
     autres
    0.90
    ″
    0.90
     불구하고
    0.89
    目錄
    0.87
    েন্ড
    0.83
    ังส
    0.78
     chercher
    0.78
    صة
    0.77
    waitForIdleSync
    0.77
     plaisir
    0.77
    POSITIVE LOGITS
    办法
    1.04
    listView
    1.04
     intimidating
    0.99
     atherosclerosis
    0.98
    Bitmap
    0.98
    辙
    0.95
     salicylate
    0.94
    س
    0.94
    fool
    0.92
    AT
    0.92
    Activations Density 0.043%

    No Known Activations