© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3464
    Prev
    Next
    INDEX
    Explanations

    Boeing 747

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     mycorrh
    2.14
    navy
    1.98
     glioma
    1.92
    ू
    1.88
     chère
    1.86
     garden
    1.86
    
    1.85
     fertility
    1.82
    ą
    1.80
     astronomer
    1.80
    POSITIVE LOGITS
    ata
    1.72
    ція
    1.69
    де
    1.64
    nel
    1.61
    ers
    1.61
    För
    1.61
    el
    1.58
    imposed
    1.57
    am
    1.57
    er
    1.56
    Activations Density 0.002%

    No Known Activations