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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260343
    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
    美好
    1.19
    িয়া
    1.09
     bestimmt
    1.03
    ъ
    1.01
     причины
    1.01
    uels
    0.96
    ವ
    0.96
    值为
    0.95
    ধর্ম
    0.94
    
    0.94
    POSITIVE LOGITS
    ט
    1.40
    טל
    1.38
    ème
    1.35
    י
    1.32
     dever
    1.31
    ం
    1.23
    жник
    1.21
    tidak
    1.21
    д
    1.20
     Namun
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.