© 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. 10802
    Prev
    Next
    INDEX
    Explanations

    words related to business and administration

    oai_token-act-pair · gemini-2.0-flash

    technical/business excerpts

    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>
    -0.52
    ob
    -0.48
    lapsingToolbar
    -0.44
     ungef
    -0.42
     Aler
    -0.42
    ↵↵
    -0.41
    drawSprites
    -0.40
    @
    -0.40
    Poloha
    -0.40
     leto
    -0.39
    POSITIVE LOGITS
    ConstraintMaker
    1.03
     AssemblyCulture
    1.00
    awtextra
    0.99
     мәкал
    0.93
     InputDecoration
    0.93
    InjectAttribute
    0.91
    SequentialGroup
    0.90
     صوتيه
    0.89
    tagHelperRunner
    0.86
    下载附件
    0.85
    Activations Density 3.771%

    No Known Activations