© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256531
    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_10_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
     дописа
    1.33
    ്രാ
    1.22
    繆
    1.22
     zde
    1.17
     Browser
    1.17
    捱
    1.16
     үш
    1.13
     salinity
    1.12
     divisors
    1.08
    ॉट
    1.08
    POSITIVE LOGITS
    ᐉ
    1.31
    seau
    1.21
     والأ
    1.16
    гү
    1.15
    dataLayer
    1.11
    Perspective
    1.11
    nel
    1.08
    الأ
    1.07
    ঁর
    1.04
    "])
    1.04
    Activations Density 0.000%

    No Known Activations