© 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. 3599
    Prev
    Next
    INDEX
    Explanations

    "not bad"

    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
     outbursts
    1.90
    靂
    1.76
     hallmarks
    1.71
     tenets
    1.67
     organelles
    1.63
     resumes
    1.62
    માં
    1.59
     preconditions
    1.57
     ductility
    1.57
    +"/"+
    1.56
    POSITIVE LOGITS
    ángulo
    1.80
    ं
    1.75
    sidebar
    1.70
    angled
    1.67
     zuen
    1.60
     pomeriggio
    1.55
     cua
    1.53
     можа
    1.51
    átor
    1.50
    Tr
    1.49
    Activations Density 0.000%

    No Known Activations