© 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. 5216
    Prev
    Next
    INDEX
    Explanations

    android layout attributes and identifiers

    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_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
    on
    0.78
    ্ব
    0.63
    ो
    0.61
    ain
    0.60
    ногда
    0.56
    xiety
    0.56
     मारे
    0.56
    ])
    0.55
    و
    0.55
    которые
    0.54
    POSITIVE LOGITS
    
    0.57
    อร์
    0.57
     totam
    0.52
    磡
    0.51
     incomes
    0.51
    crs
    0.50
    tela
    0.49
     pajak
    0.49
     скло
    0.48
     lenses
    0.48
    Activations Density 0.001%

    No Known Activations