© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15942
    Prev
    Next
    INDEX
    Explanations

    text mentioning CDC estimates about health risks for older adults

    oai_token-act-pair · gemini-2.0-flash

    mixed texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     similar
    -0.56
    cence
    -0.48
    similar
    -0.47
     est
    -0.46
    hending
    -0.46
     contact
    -0.46
     ag
    -0.45
    ⅼ
    -0.44
    нео
    -0.44
     ox
    -0.44
    POSITIVE LOGITS
    certainly
    1.06
    Certainly
    1.01
     Certainly
    0.95
     certainly
    0.95
     Chwiliwch
    0.91
    GEBURTSDATUM
    0.90
    InjectAttribute
    0.89
     CreateTagHelper
    0.85
    Probably
    0.81
    脚注の使い方
    0.80
    Activations Density 0.795%

    No Known Activations