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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4611
    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_5_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
     dass
    0.91
     ставка
    0.87
     gql
    0.86
    ра
    0.85
     mida
    0.84
    }"
    0.84
     поня
    0.81
    呃
    0.80
     atenção
    0.80
     terrest
    0.79
    POSITIVE LOGITS
    गरी
    0.95
    сиз
    0.90
    vii
    0.88
    ol
    0.87
    ad
    0.84
    witch
    0.83
    🏿
    0.83
    can
    0.83
    ginas
    0.83
    ccess
    0.83
    Activations Density 0.007%

    No Known Activations