© 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. 8357
    Prev
    Next
    INDEX
    Explanations

    ui design

    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
    胞
    2.71
    р
    2.66
    ate
    2.61
     ahol
    2.60
    ように
    2.53
     tandem
    2.48
     unmet
    2.46
    াদ
    2.46
    contador
    2.39
     valamint
    2.39
    POSITIVE LOGITS
    い
    2.76
     adhere
    2.71
    ל
    2.58
    ের
    2.53
    isenberg
    2.50
    দিন
    2.48
    ারন
    2.45
     schreibt
    2.43
    يين
    2.40
    vur
    2.35
    Activations Density 0.000%

    No Known Activations