© 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. 3678
    Prev
    Next
    INDEX
    Explanations

    years like 2024

    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
    ar
    1.41
    arh
    1.06
    arag
    0.96
    arono
    0.92
    er
    0.87
    다
    0.86
    ively
    0.81
    ergy
    0.79
    ories
    0.78
    SOC
    0.78
    POSITIVE LOGITS
     progn
    1.08
    ن
    0.98
     पर्यंत
    0.95
     parton
    0.91
    фектив
    0.88
    पर्यंत
    0.87
    韆
    0.87
    ylül
    0.85
    ्यू
    0.85
     demeure
    0.83
    Activations Density 0.024%

    No Known Activations