© 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. 7927
    Prev
    Next
    INDEX
    Explanations

    presenting

    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
    й
    3.40
    ర్
    3.31
     potrivit
    3.21
    да
    3.16
    م
    2.99
    asında
    2.91
    ený
    2.87
     jost
    2.87
    𝘯
    2.72
    𝘵
    2.72
    POSITIVE LOGITS
    та
    3.97
     собой
    3.29
     accounted
    3.11
    ین
    3.07
    lb
    2.85
    с
    2.79
    मर्श
    2.66
    𝗁
    2.64
     umum
    2.64
    lere
    2.61
    Activations Density 0.055%

    No Known Activations