© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7223
    Prev
    Next
    INDEX
    Explanations

    redundancy

    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
    ك
    2.05
    ج
    2.03
    িং
    2.01
    म
    2.00
    मिताभ
    1.99
    时候
    1.97
     누가
    1.96
    б
    1.93
    뢨
    1.93
    Antae
    1.91
    POSITIVE LOGITS
    ^{
    2.02
     mesta
    2.00
     getIntent
    1.92
    ordinaire
    1.90
    р
    1.89
    _{
    1.88
    剰
    1.87
     lu
    1.81
    ‬‬
    1.79
    ئات
    1.77
    Activations Density 0.028%

    No Known Activations