© 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. 5654
    Prev
    Next
    INDEX
    Explanations

    util

    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
    ि
    2.44
     грн
    2.40
    ụ
    2.37
    ებლ
    2.36
    টি
    2.36
     bilo
    2.34
    אם
    2.31
    rative
    2.25
    ated
    2.25
    withstanding
    2.23
    POSITIVE LOGITS
    
    2.61
    ienced
    2.33
    ✐
    2.27
    ד
    2.26
     pim
    2.24
    textBox
    2.23
    गी
    2.22
    
    2.21
    ز
    2.21
    uels
    2.19
    Activations Density 0.001%

    No Known Activations