© 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. 8341
    Prev
    Next
    INDEX
    Explanations

    Gateway, Insights, Situations

    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
    ي
    1.60
    い
    1.57
    ت
    1.57
    ು
    1.54
    ਕ
    1.48
    ോ
    1.46
    ៉
    1.46
    ल
    1.46
    െ
    1.44
    س
    1.41
    POSITIVE LOGITS
    ﺙ
    1.17
    $('
    1.13
    ()=>{
    1.06
     indiv
    1.06
    شهاد
    1.03
     شاید
    1.01
    $(".
    1.01
    ȱ
    1.01
    ﻧ
    0.99
    Weitere
    0.99
    Activations Density 0.000%

    No Known Activations