© 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. 4039
    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
     CYP
    0.31
     सारी
    0.30
    蓣
    0.30
    𝔰
    0.28
     CFR
    0.26
     CMD
    0.26
    licking
    0.25
     والط
    0.25
     CBIT
    0.25
    डेड
    0.25
    POSITIVE LOGITS
     materna
    0.32
    нт
    0.31
    ا
    0.31
    𝙞
    0.30
     gestaltet
    0.29
    적인
    0.29
    mov
    0.28
    ה
    0.28
    л
    0.28
    ቪ
    0.27
    Activations Density 0.001%

    No Known Activations