© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3310
    Prev
    Next
    INDEX
    Explanations

    woven into texture or concept

    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
     Figur
    0.85
    涔
    0.84
     Caesar
    0.81
    ەت
    0.81
     prostaglandin
    0.80
     inch
    0.80
    ForKey
    0.78
     cemeteries
    0.77
    ore
    0.76
     чем
    0.76
    POSITIVE LOGITS
    ताई
    1.16
     طريق
    1.15
     ribbons
    1.11
    𝐀
    1.09
     asunto
    1.06
    ුණ
    1.06
    織
    1.05
    ี
    1.04
    체의
    1.04
     twine
    1.03
    Activations Density 0.036%

    No Known Activations