© 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. 7068
    Prev
    Next
    INDEX
    Explanations

    javascript fs

    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
    ために
    1.62
    ाय
    1.62
    CES
    1.60
    
    1.60
    لة
    1.59
    يكي
    1.51
     worst
    1.47
     боль
    1.45
    θε
    1.45
    ている
    1.45
    POSITIVE LOGITS
     enlightening
    1.81
     stap
    1.72
     latina
    1.62
     odv
    1.58
    ⼒
    1.58
    ‖</
    1.55
     vectores
    1.52
     provident
    1.52
    اضره
    1.51
     suced
    1.51
    Activations Density 0.003%

    No Known Activations