© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    user interface, experience, research

    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_5_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
     থেকেই
    1.43
     suerte
    1.41
     bothers
    1.35
    歉
    1.32
    ある
    1.28
    calcular
    1.26
    로운
    1.25
    ें
    1.21
     ২০১৮
    1.20
    в
    1.17
    POSITIVE LOGITS
     reprend
    1.74
    re
    1.51
     pleinement
    1.47
    isocyanate
    1.43
     Prü
    1.43
    
    1.41
    கி
    1.40
     telle
    1.39
     mitotic
    1.39
     Microbial
    1.38
    Activations Density 0.138%

    No Known Activations