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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259041
    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
    k
    1.35
     carbides
    1.22
    이번
    1.15
    й
    1.14
     oint
    1.12
     Supp
    1.12
     dej
    1.11
    aching
    1.11
     contingencies
    1.10
    你有
    1.10
    POSITIVE LOGITS
    ին
    1.44
    siniz
    1.29
    ebilir
    1.21
    স্ট
    1.16
    𝐨
    1.15
     hơi
    1.14
    ዚያ
    1.14
    melier
    1.13
    𝐥
    1.12
    ćem
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.