© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9591
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    Wilson
    0.75
     பண
    0.75
     berupa
    0.75
    
    0.74
    asing
    0.74
    Dep
    0.73
     Wilson
    0.73
    资金
    0.72
    
    0.72
    
    0.71
    POSITIVE LOGITS
     দেয়
    0.62
    pectral
    0.61
    lin
    0.59
     specializes
    0.59
    lub
    0.58
     mechanized
    0.57
    渐
    0.57
     দেয়
    0.57
     mechanics
    0.57
    記憶
    0.56
    Activations Density 0.005%

    No Known Activations