© 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. 3942
    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
    Not in Any Lists

    No Comments

    Negative Logits
     dant
    1.85
     konu
    1.76
     osobow
    1.74
     décro
    1.70
    𝚞
    1.68
    ਜ਼
    1.68
    𝚍
    1.68
    ्स
    1.67
    𝚗
    1.65
    এদিকে
    1.64
    POSITIVE LOGITS
    𝘴
    2.41
    𝘦
    2.09
    𝘰
    1.97
    𝘢
    1.82
    𝘧
    1.79
    𝘥
    1.77
    𝘤
    1.77
    𝘩
    1.72
    𝘯
    1.71
     glossy
    1.70
    Activations Density 0.005%

    No Known Activations