© 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. 3962
    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
    tion
    2.12
    tive
    2.03
    tions
    1.71
    ं
    1.49
    metre
    1.40
    Tov
    1.40
    ten
    1.39
    rahm
    1.36
    nya
    1.35
    était
    1.35
    POSITIVE LOGITS
     hela
    1.59
    انية
    1.57
     createdAt
    1.57
    actionBar
    1.57
    avnom
    1.53
    鏄
    1.51
    예
    1.50
    лох
    1.48
     поиска
    1.48
     ditt
    1.46
    Activations Density 0.006%

    No Known Activations