© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5441
    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_3_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
     Daar
    0.74
     hice
    0.69
     súa
    0.68
     Более
    0.66
    剌
    0.66
     noqa
    0.65
    iato
    0.64
     }^{*}$
    0.63
     entste
    0.62
    ॉक
    0.62
    POSITIVE LOGITS
    リ
    0.80
    ون
    0.78
    five
    0.77
    ियमित
    0.76
    
    0.75
    Cheers
    0.74
    cultured
    0.74
     hairstyles
    0.74
    мимо
    0.74
    را
    0.73
    Activations Density 0.001%

    No Known Activations