© 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-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209514
    Prev
    Next
    INDEX
    Explanations

    Col-0 or born

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     उपहार
    0.45
    ucksack
    0.44
     безопасности
    0.43
    缺点
    0.42
     защиту
    0.42
    <unused25>
    0.41
    𝗸
    0.41
     защиты
    0.41
    ודה
    0.40
    spannung
    0.40
    POSITIVE LOGITS
    ദീ
    0.38
     dioxygen
    0.36
    ັ
    0.35
    erys
    0.35
    增
    0.33
     thus
    0.33
     {
    0.33
    โลก
    0.33
     daraus
    0.33
     yeah
    0.32
    Activations Density 0.000%

    No Known Activations