© 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. 5132
    Prev
    Next
    INDEX
    Explanations

    search for models

    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
    ar
    1.48
    ي
    1.46
     хоть
    1.38
     একই
    1.36
    arh
    1.36
    ના
    1.31
     diseg
    1.30
    在
    1.29
    al
    1.26
    he
    1.25
    POSITIVE LOGITS
    ക്കുറിച്ച്
    1.79
     метра
    1.63
    تع
    1.62
    どうぞ
    1.61
     rxjs
    1.59
     cxb
    1.56
    xico
    1.51
    که
    1.51
    போன்ற
    1.50
    께
    1.49
    Activations Density 0.004%

    No Known Activations