© 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. 8884
    Prev
    Next
    INDEX
    Explanations

    printing output in code

    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
    ش
    2.82
    тата
    2.61
    ن
    2.58
    n
    2.54
    ب
    2.49
    ни
    2.42
    دون
    2.40
    rut
    2.38
    بيه
    2.36
    nál
    2.30
    POSITIVE LOGITS
     불구하고
    2.72
    何の
    2.40
    𝗴
    2.39
     anden
    2.32
     []:
    2.30
     davantage
    2.24
     fact
    2.19
     dint
    2.17
    onload
    2.15
    ंजलि
    2.15
    Activations Density 0.001%

    No Known Activations