© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3362
    Prev
    Next
    INDEX
    Explanations

    boat, canoe, kayaking, cruise, river trip

    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
    ्स
    1.12
    𝗮
    1.06
    ra
    0.98
     Şubat
    0.84
    
    0.83
    nya
    0.82
     destinés
    0.80
    та
    0.79
    ihe
    0.78
    ಿರುವ
    0.78
    POSITIVE LOGITS
    艇
    1.28
    ع
    1.10
    𝓂
    1.06
     canoe
    1.06
     sungai
    1.03
    鴦
    1.02
    𝙽
    1.01
     Nile
    1.01
    𝓌
    0.97
    boat
    0.97
    Activations Density 0.079%

    No Known Activations