© 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. 4126
    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
    acqu
    2.93
    fei
    2.80
    থাৎ
    2.72
     пока
    2.69
    не
    2.68
    𝒍
    2.67
    𝒉
    2.64
    k
    2.60
    ※
    2.56
    𝒌
    2.55
    POSITIVE LOGITS
     hark
    3.23
    ᴄ
    2.74
    ல்
    2.68
    <bos>
    2.66
     vervolgens
    2.49
    ᴇ
    2.45
     maxillary
    2.44
    ʙ
    2.43
    んばんは
    2.42
    ʟ
    2.40
    Activations Density 0.047%

    No Known Activations