© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10016
    Prev
    Next
    INDEX
    Explanations

    words related to management, legal, and government

    oai_token-act-pair · gemini-2.0-flash

    legal and news contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.63
    findpost
    -0.49
    ViewFeatures
    -0.45
     direct
    -0.41
     ,
    -0.40
     “
    -0.40
     das
    -0.39
     Reserve
    -0.39
     lòng
    -0.39
     -
    -0.38
    POSITIVE LOGITS
     itſelf
    0.82
     NUKAT
    0.79
     pleaſure
    0.75
     Majefty
    0.74
     leaſt
    0.74
     vectorstock
    0.73
     Anſ
    0.73
     ſeveral
    0.72
     doubtnut
    0.72
     Eſ
    0.71
    Activations Density 4.819%

    No Known Activations