© 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. 7083
    Prev
    Next
    INDEX
    Explanations

    diesel generator, engine, fuel

    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
    л
    2.98
     cations
    2.88
     тим
    2.78
     й
    2.74
    ૦
    2.72
    
    2.56
    ت
    2.56
     spie
    2.48
     introns
    2.47
    स
    2.47
    POSITIVE LOGITS
    ূতন
    2.69
    ਤ
    2.55
    வே
    2.51
    cupertino
    2.51
    জো
    2.41
    terase
    2.31
    ğı
    2.30
    cimento
    2.29
    m
    2.27
    p
    2.26
    Activations Density 0.020%

    No Known Activations