© 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
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5042
    Prev
    Next
    INDEX
    Explanations

    can, may, cash, anti

    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
    া
    0.58
    ;|
    0.56
    𝙞
    0.54
    𝙖
    0.51
    Encyclopedia
    0.51
    soup
    0.50
    
    0.50
     seedling
    0.50
    
    0.50
    кого
    0.49
    POSITIVE LOGITS
     дорогие
    0.47
    ار
    0.46
    quint
    0.46
    𓂀
    0.45
     impregnated
    0.45
    स्परिक
    0.44
    Ფ
    0.44
     inscribed
    0.44
    uš
    0.44
    n
    0.43
    Activations Density 0.168%

    No Known Activations