© 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. 8604
    Prev
    Next
    INDEX
    Explanations

    list of

    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
    োদয়
    2.15
    로
    2.14
    可以将
    2.08
    в
    1.99
    de
    1.91
    ти
    1.90
    ਸ਼
    1.87
    鍮
    1.84
    ਆਂ
    1.83
    ../
    1.83
    POSITIVE LOGITS
     excuses
    2.28
    unstyled
    2.25
    Selon
    2.22
    ု
    2.22
    ENER
    2.16
    ة
    2.09
    hoppers
    2.08
    به
    2.04
    ভুক্ত
    2.01
     przeb
    1.97
    Activations Density 0.091%

    No Known Activations