© 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. 12924
    Prev
    Next
    INDEX
    Explanations

    medical texts, especially ones related to surgery and dentistry

    oai_token-act-pair · gemini-2.0-flash

    dentistry and surgery

    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
     Audiodateien
    -0.47
    <h5>
    -0.46
     Fast
    -0.45
    PageContext
    -0.45
    reis
    -0.43
     Influence
    -0.43
     internetowa
    -0.42
    #![
    -0.42
    振り
    -0.42
    influence
    -0.41
    POSITIVE LOGITS
     tartalomajánló
    0.82
    évaluateur
    0.76
     CreateTagHelper
    0.76
     ProtoMessage
    0.71
     >=",
    0.71
     EconPapers
    0.69
    AndEndTag
    0.68
    titleMargin
    0.67
    aarrggbb
    0.67
    thâu
    0.67
    Activations Density 1.249%

    No Known Activations