© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4028
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ங்கிணை
    3.73
    n
    3.52
    s
    3.37
    nya
    3.34
    ों
    3.08
    ات
    3.08
    noc
    3.03
    u
    2.93
    ের
    2.86
    nian
    2.82
    POSITIVE LOGITS
     fleste
    3.80
     själ
    3.33
    wolves
    3.16
    Ŷ
    3.09
     бывают
    3.02
    ⅾ
    3.02
    ԝ
    3.00
     doivent
    2.91
     हुए
    2.75
    錢
    2.74
    Activations Density 0.035%

    No Known Activations