© 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. 6601
    Prev
    Next
    INDEX
    Explanations

    strings of words related to lab work and lab tests

    oai_token-act-pair · gemini-2.0-flash

    laboratory analysis

    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
     >=",
    -0.77
     ModelExpression
    -0.71
     فريبيس
    -0.70
    UserScript
    -0.69
     varandra
    -0.67
    InjectAttribute
    -0.65
     bonté
    -0.64
    quelize
    -0.64
     compétence
    -0.64
    complexType
    -0.62
    POSITIVE LOGITS
     analysis
    0.67
     analyses
    0.65
     screening
    0.56
     measurement
    0.50
    ことができました
    0.48
     evaluation
    0.46
    msgSender
    0.46
    LARE
    0.46
    OCA
    0.46
     Analysis
    0.46
    Activations Density 7.004%

    No Known Activations