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. 4490
    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
    将
    2.18
    फा
    2.17
    InMemory
    2.08
    angleright
    2.03
    如图
    2.02
    गी
    2.02
    ফ
    1.96
    লো
    1.94
    ϻ
    1.94
    ﭔ
    1.91
    POSITIVE LOGITS
    ே
    2.35
    ce
    2.09
    悱
    2.04
    ри
    2.00
     ultrast
    1.99
    ed
    1.96
    ურ
    1.92
     نفسه
    1.92
    ী
    1.91
     helst
    1.89
    Activations Density 0.071%

    No Known Activations