© 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. 5086
    Prev
    Next
    INDEX
    Explanations

    catalyst / catalytic

    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
    ture
    2.89
    
    2.85
     experimentally
    2.77
    setMessage
    2.74
    ων
    2.73
    dealing
    2.72
    ਤਰ
    2.72
    
    2.71
    
    2.66
     dealing
    2.66
    POSITIVE LOGITS
    Ꮤ
    3.20
     слід
    2.99
    ⁺
    2.85
    𝑣
    2.84
    𝑟
    2.81
     understatement
    2.73
     ʼ
    2.69
    rypsin
    2.69
     dû
    2.68
    𝙃
    2.66
    Activations Density 0.015%

    No Known Activations