© 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. 7315
    Prev
    Next
    INDEX
    Explanations

    algorithm include

    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
     lucru
    2.88
    ية
    2.75
    <bos>
    2.58
    ので
    2.42
    কৃষ্ণ
    2.38
    ocker
    2.35
    ла
    2.29
    𝑙
    2.25
    되
    2.22
     damn
    2.22
    POSITIVE LOGITS
    assertEquals
    2.77
     wobei
    2.61
     liés
    2.56
     불구
    2.51
    رل
    2.39
     HomeComponent
    2.39
    పతి
    2.37
    र्मेंद्र
    2.34
     Ledger
    2.34
     scrapes
    2.32
    Activations Density 0.029%

    No Known Activations