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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 32
    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
    гра
    2.67
    лар
    2.36
    𝐠
    2.33
    𝐫
    2.33
    decoded
    2.32
    meson
    2.30
    𝐑
    2.28
    фектив
    2.27
    해도
    2.22
    equalsIgnoreCase
    2.19
    POSITIVE LOGITS
    缈
    3.27
    י
    2.95
    ្នាំ
    2.91
    াতাড়ি
    2.82
    kken
    2.77
    ി
    2.76
    ições
    2.66
    ॉयड
    2.63
    ख्ती
    2.63
    ε
    2.63
    Activations Density 0.080%

    No Known Activations