© 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. 8771
    Prev
    Next
    INDEX
    Explanations

    1973 and dates

    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
    стью
    2.52
    تف
    2.41
     eligible
    2.33
    Comparer
    2.29
     parecido
    2.28
    ammatory
    2.28
    𝗌
    2.26
    bladder
    2.24
    ={\
    2.23
    yilda
    2.17
    POSITIVE LOGITS
    ра
    4.34
    ের
    2.74
    ../
    2.64
    б
    2.46
    œil
    2.44
    ند
    2.44
    pele
    2.44
     обслуживание
    2.42
     kapas
    2.42
    উন্ট
    2.36
    Activations Density 0.036%

    No Known Activations