© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    famous surnames and associated people

    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
    ா
    0.66
    jLabel
    0.63
    il
    0.63
    로
    0.61
    koliko
    0.61
    סף
    0.59
    is
    0.59
    umum
    0.59
    чие
    0.59
    に
    0.59
    POSITIVE LOGITS
    рачи
    0.65
    ِين
    0.63
    nons
    0.63
    rég
    0.61
    notch
    0.61
    dep
    0.60
    खास्त
    0.59
     presa
    0.58
    ﺮ
    0.57
    餑
    0.57
    Activations Density 0.023%

    No Known Activations