© 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. 6938
    Prev
    Next
    INDEX
    Explanations

    main() function

    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
    ا
    2.70
     certainly
    2.29
     admittedly
    2.08
     Tä
    1.93
    IgnoreCase
    1.92
    毕竟
    1.88
     clave
    1.87
    伙
    1.84
    siniz
    1.82
    ulation
    1.82
    POSITIVE LOGITS
    an
    3.08
    te
    2.16
    ದಾರ
    2.16
    fant
    2.07
    𝘨
    2.01
    ان
    2.00
    ين
    1.99
    म
    1.98
    وحة
    1.98
    andet
    1.97
    Activations Density 0.006%

    No Known Activations