© 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. 2075
    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
    с
    2.36
    ου
    2.33
     samym
    2.32
    r
    2.31
     annet
    2.19
    고
    2.15
    트
    2.05
    ר
    2.04
    н
    2.03
    为空
    2.02
    POSITIVE LOGITS
    +}(
    1.97
    atemala
    1.93
    ništva
    1.89
    การณ์
    1.87
    WERS
    1.85
    RPM
    1.83
    linson
    1.82
    Virt
    1.81
    样子
    1.80
     अकॉर्डिंग
    1.79
    Activations Density 0.003%

    No Known Activations