© 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. 4079
    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
    maximizing
    1.60
    et
    1.38
    𝗽
    1.35
     liberalization
    1.35
     depriving
    1.35
     hardness
    1.34
    𝗶
    1.33
    mathspace
    1.32
    Ive
    1.31
    🫣
    1.31
    POSITIVE LOGITS
    다
    1.74
    ce
    1.42
    و
    1.42
    unakan
    1.36
     offenbar
    1.36
    quela
    1.32
     compless
    1.30
     oc
    1.29
    ється
    1.28
    Одно
    1.28
    Activations Density 0.003%

    No Known Activations