© 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. 8021
    Prev
    Next
    INDEX
    Explanations

    trained on

    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
    要
    2.61
    یه
    2.60
    le
    2.60
    mandatory
    2.47
    weight
    2.35
    imread
    2.29
    िंग
    2.28
    blow
    2.25
    ,\,\,\,\
    2.24
    o
    2.22
    POSITIVE LOGITS
     oxen
    2.65
    Ри
    2.23
     arus
    2.21
    榇
    2.16
    Ра
    2.11
    //*
    2.02
    Мы
    2.02
     mince
    2.01
    قب
    1.99
    Peaks
    1.99
    Activations Density 0.101%

    No Known Activations