© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4993
    Prev
    Next
    INDEX
    Explanations

    danbooru tags

    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
    yaw
    0.63
     avocat
    0.62
    ਰ
    0.62
    ע
    0.61
    ্রো
    0.60
     nominal
    0.60
     cose
    0.59
     acclaim
    0.58
    х
    0.58
    RENCE
    0.57
    POSITIVE LOGITS
    त
    0.70
    
    0.65
    Ƹ
    0.65
    珑
    0.64
     والمع
    0.64
    
    0.64
    т
    0.64
    👉
    0.63
    
    0.63
    ᅵ
    0.63
    Activations Density 0.002%

    No Known Activations