© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257543
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     subconscious
    1.27
    ்
    1.27
     [&](
    1.23
     subconsciously
    1.19
     खरीदें
    1.17
    و
    1.11
    니
    1.11
    ierta
    1.11
    ਰੀ
    1.11
     handful
    1.09
    POSITIVE LOGITS
    뇌
    1.27
     seves
    1.26
     pubblici
    1.20
    ษัท
    1.19
    нуу
    1.13
    ciò
    1.11
     системи
    1.11
    alphabet
    1.10
    categorie
    1.09
     мали
    1.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.