© 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. 9030
    Prev
    Next
    INDEX
    Explanations

    Example Usage:

    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
    ق
    2.03
    m
    1.75
    𝚑
    1.74
    ্ত
    1.73
    ра
    1.70
    𝚊
    1.66
    жды
    1.62
    брать
    1.62
    ू
    1.61
    tete
    1.60
    POSITIVE LOGITS
    া
    2.18
    नाल्ड
    2.07
    a
    2.06
     wholes
    2.03
    я
    2.03
     टुडे
    1.99
     asalamualaikum
    1.94
    slope
    1.91
     jsonify
    1.90
     tämä
    1.85
    Activations Density 0.008%

    No Known Activations