© 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-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 120712
    Prev
    Next
    INDEX
    Explanations

    components used to generate output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_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
     bere
    0.42
     আনুশকা
    0.39
     量
    0.37
     sadr
    0.37
     gül
    0.37
    ineux
    0.36
     odby
    0.36
     벌
    0.36
     터
    0.36
     berakhir
    0.35
    POSITIVE LOGITS
     install
    0.46
    インストール
    0.44
    install
    0.42
    安装
    0.41
    安裝
    0.40
    Install
    0.40
     fiberglass
    0.39
    rchen
    0.38
     installed
    0.38
     Install
    0.38
    Activations Density 0.007%

    No Known Activations