© 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. 3936
    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
    𝑡
    3.67
    𝑦
    3.45
    selves
    3.24
    Contrary
    3.22
    ग्विजय
    3.03
    Featuring
    2.98
    𝑣
    2.92
    Considering
    2.89
    Celebrate
    2.84
     quantifying
    2.82
    POSITIVE LOGITS
    م
    3.38
    in
    2.96
    at
    2.61
    maßen
    2.42
    ви
    2.41
    ة
    2.39
    ere
    2.32
    as
    2.31
    posium
    2.29
    렇
    2.24
    Activations Density 0.012%

    No Known Activations