© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9026
    Prev
    Next
    INDEX
    Explanations

    17th century

    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
    Negative Logits
    ्य
    3.35
    ن
    3.14
    ायतों
    3.01
    hoa
    2.93
    ي
    2.91
    ীয়
    2.79
    ください
    2.78
    ிருக்கும்
    2.75
    erol
    2.71
     casser
    2.69
    POSITIVE LOGITS
    ある
    2.89
     tide
    2.80
    ळे
    2.76
    ^{*}
    2.66
    বীন্দ্রনাথ
    2.64
    𝑢
    2.59
    ством
    2.56
     oscura
    2.56
    cake
    2.51
    CodeableConcept
    2.48
    Activations Density 0.099%

    No Known Activations