© 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. 9159
    Prev
    Next
    INDEX
    Explanations

    job position or role

    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
     со
    1.40
    ट
    1.12
    _{
    1.09
     ponctu
    1.09
     कहने
    1.08
    lesson
    1.05
     mise
    1.04
    ^{
    1.03
    quarters
    0.99
     पौ
    0.98
    POSITIVE LOGITS
    e
    1.36
    你
    1.21
    ことにより
    1.20
    tedir
    1.19
    হ
    1.18
     culpable
    1.14
    eel
    1.11
    একটি
    1.10
     Kristi
    1.07
     Jacinto
    1.06
    Activations Density 0.232%

    No Known Activations