© 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. 258746
    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
    ти
    1.51
    с
    1.25
    ilmiş
    1.22
    рах
    1.17
    diffusion
    1.15
    glfw
    1.15
    다
    1.15
    व्ह
    1.15
     миллионов
    1.13
    र्गन
    1.12
    POSITIVE LOGITS
    ÉE
    1.35
    
    1.25
    传统
    1.12
    жні
    1.12
    话说
    1.12
     carriages
    1.12
    ees
    1.11
     traditions
    1.10
    ecake
    1.10
    精英
    1.10
    Activations Density 0.000%

    No Known Activations