© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9222
    Prev
    Next
    INDEX
    Explanations

    activity related nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    त
    2.93
     healed
    2.76
    кция
    2.68
    Conversely
    2.66
    behaved
    2.56
    Likewise
    2.51
     irradiance
    2.49
    ਾ
    2.49
    ל
    2.46
     equivariant
    2.45
    POSITIVE LOGITS
     extrav
    2.76
     partielle
    2.74
     conversation
    2.34
     sehari
    2.30
    >(){
    2.27
    ˵
    2.26
    
    2.24
    IDADES
    2.23
    ир
    2.23
    ins
    2.19
    Activations Density 0.039%

    No Known Activations