© 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. 8078
    Prev
    Next
    INDEX
    Explanations

    rust file paths

    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
    े
    3.09
    𝖎
    2.96
    ে
    2.86
    ीन
    2.84
    то
    2.83
    iw
    2.68
    en
    2.66
    कर
    2.64
    rencies
    2.62
    src
    2.61
    POSITIVE LOGITS
    bí
    2.67
    ل
    2.61
    ۜ
    2.59
    le
    2.54
     dend
    2.52
    đ
    2.52
    바로
    2.44
    일
    2.43
    ס
    2.42
    ϻ
    2.41
    Activations Density 0.002%

    No Known Activations