© 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. 5099
    Prev
    Next
    INDEX
    Explanations

    GeeksforGeeks and Soul Entertainment

    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
     textColor
    1.34
    
    1.27
    ين
    1.26
     propio
    1.14
     própria
    1.12
     ganglia
    1.10
    ء
    1.10
     rodz
    1.10
     parlement
    1.10
    ී
    1.09
    POSITIVE LOGITS
    is
    1.24
    р
    1.23
     tenfold
    1.21
    SIS
    1.20
    ت
    1.16
    hx
    1.15
    মন
    1.12
     എന്നാല്‍
    1.11
    acidad
    1.11
    轫
    1.09
    Activations Density 0.007%

    No Known Activations