© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5514
    Prev
    Next
    INDEX
    Explanations

    Ho'oponopono "I'm sorry"

    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
    jší
    1.92
     mechanistic
    1.58
    तत्
    1.54
    т
    1.53
    त
    1.48
     groceries
    1.47
     dire
    1.47
    تين
    1.46
     findPlayer
    1.44
     hydrolysis
    1.43
    POSITIVE LOGITS
    メント
    1.88
    qvarna
    1.82
    
    1.82
     aws
    1.74
    expand
    1.68
    🅐
    1.61
    cinn
    1.57
    
    1.57
    elijke
    1.54
     distinct
    1.53
    Activations Density 0.012%

    No Known Activations