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. 4103
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    synchronized
    2.04
    aqu
    1.92
    y
    1.86
    als
    1.69
    typeparam
    1.55
    ressed
    1.55
    colspan
    1.52
    ei
    1.52
    clearly
    1.51
    invasive
    1.51
    POSITIVE LOGITS
    𝖊
    2.46
    
    2.12
    𝖎
    2.10
     
    2.10
    ल
    2.09
    на
    1.99
    
    1.95
    
    1.94
     freelancers
    1.92
     jumlah
    1.89
    Activations Density 0.000%

    No Known Activations