© 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. 7842
    Prev
    Next
    INDEX
    Explanations

    payment or advertising

    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
    NAMEN
    0.58
    uern
    0.57
    ı
    0.57
     sogenannte
    0.57
    詐
    0.57
     repellent
    0.55
     wrestle
    0.55
    ıları
    0.54
    🟠
    0.54
     lobe
    0.53
    POSITIVE LOGITS
     인한
    0.56
     인해
    0.52
    р
    0.50
     eds
    0.50
    ፍተኛ
    0.49
    rj
    0.49
    действие
    0.48
    قاف
    0.47
    یه
    0.47
     создан
    0.46
    Activations Density 0.093%

    No Known Activations