© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 822
    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
    ية
    3.79
    к
    3.75
    ến
    3.62
    ย
    3.43
    ット
    3.42
     supposed
    3.35
    ה
    3.34
    getting
    3.26
    whitespace
    3.11
    ۩
    3.09
    POSITIVE LOGITS
     been
    5.41
     sido
    4.06
     vært
    3.93
    at
    3.73
     BEEN
    3.68
     varit
    3.48
    been
    3.35
     været
    3.22
    pyrimidin
    3.11
     Been
    3.05
    Activations Density 0.068%

    No Known Activations