© 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. 8998
    Prev
    Next
    INDEX
    Explanations

    in code related to Activity

    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
     arriba
    1.74
    ively
    1.58
    ма
    1.54
    πει
    1.49
    permutation
    1.49
    お子
    1.47
     đón
    1.47
     postérieures
    1.43
     중심으로
    1.40
    ش
    1.39
    POSITIVE LOGITS
    те
    1.69
    ҹ
    1.68
    𝙠
    1.65
    幂
    1.61
    襞
    1.60
    ৭
    1.58
    耖
    1.54
    ческие
    1.54
    ◦
    1.53
     exceeding
    1.52
    Activations Density 0.001%

    No Known Activations