© 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. 4768
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    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
    ু
    1.30
    u
    1.21
    ForeColor
    1.17
    o
    1.15
    ర్
    1.07
     enforcing
    1.05
    uders
    1.03
    oed
    1.01
    
    1.00
    ૂર્ણ
    1.00
    POSITIVE LOGITS
     već
    1.11
    Па
    1.10
     голов
    1.08
    দৃ
    1.00
     гэта
    0.99
    经营
    0.99
    ح
    0.99
    А
    0.98
    ও
    0.98
     thiết
    0.97
    Activations Density 0.735%

    No Known Activations