© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3616
    Prev
    Next
    INDEX
    Explanations

    separated by

    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_5_width_262k_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
    言う
    1.28
    ons
    1.25
    зи
    1.10
    その
    1.09
    y
    1.08
    шты
    1.08
    <bos>
    1.06
    પ
    1.02
     दग
    1.02
    ^{
    1.00
    POSITIVE LOGITS
     بندی
    1.33
    anyol
    1.19
    녓
    1.16
     Telangana
    1.15
    禍
    1.11
    curvature
    1.10
     Kippur
    1.09
     Mosque
    1.09
    レシ
    1.07
     Masjid
    1.07
    Activations Density 0.037%

    No Known Activations