© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260184
    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_10_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
    4
    1.21
    其
    1.20
    2
    1.17
    ch
    1.15
    na
    1.13
    ح
    1.12
    1
    1.07
    r
    1.07
    7
    1.07
    nae
    1.04
    POSITIVE LOGITS
     scrollView
    1.53
    Ⲉ
    1.25
    阚
    1.24
    Puede
    1.22
     ένας
    1.20
    lamualaikum
    1.17
    ﺐ
    1.15
     upang
    1.15
     来
    1.15
    বৃত্তি
    1.15
    Activations Density 0.000%

    No Known Activations