Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3925
    Prev
    Next
    INDEX
    Explanations

    code use statements

    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
    र
    0.59
    ला
    0.54
    quela
    0.54
    ction
    0.51
     osob
    0.51
    ងារ
    0.51
    près
    0.49
    cing
    0.49
    abouts
    0.49
    й
    0.48
    POSITIVE LOGITS
    
    0.51
     με
    0.48
     privati
    0.47
     zoos
    0.46
     depicted
    0.46
     Dense
    0.46
     ligger
    0.46
    
    0.45
    িল
    0.45
    ீன்
    0.45
    Activations Density 0.001%

    No Known Activations