© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2061
    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_2_width_16k_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
    ן
    1.44
    ്രി
    1.43
    வும்
    1.40
    ीन
    1.39
    ুন
    1.35
    för
    1.32
    가의
    1.32
    ስ
    1.28
     समक्ष
    1.27
    y
    1.27
    POSITIVE LOGITS
     تعالى
    1.68
     facendo
    1.62
    formas
    1.60
    𝘮
    1.59
    TT
    1.58
    
    1.57
    ⺀
    1.54
    ار
    1.54
    𝘫
    1.52
    𝘷
    1.51
    Activations Density 0.575%

    No Known Activations