Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261221
    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
     माध्यम
    1.07
     নব
    1.07
     Nesse
    1.07
     alternately
    1.05
     lợi
    1.02
    oretically
    1.01
     içi
    1.00
    \{(
    1.00
    ණ්ඩ
    0.99
    Employee
    0.98
    POSITIVE LOGITS
    Ру
    1.27
    pubescens
    1.23
    ◘
    1.21
    nio
    1.20
     craindre
    1.18
    nia
    1.17
     susceptibles
    1.16
    Σ
    1.16
    Э
    1.16
    ні
    1.15
    Activations Density 0.000%

    No Known Activations