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. 261848
    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
    َان
    1.26
    ibility
    1.17
    ित
    1.14
     लाह
    1.12
    <unused350>
    1.09
     cockro
    1.08
    एस
    1.07
    ック
    1.06
     Skyscrapers
    1.06
    𠃊
    1.05
    POSITIVE LOGITS
     ^{
    1.35
    ي
    1.26
     ale
    1.23
    다
    1.23
    
    1.22
    worn
    1.21
    가
    1.17
     cât
    1.17
     되
    1.17
    าค
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.