© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14049
    Prev
    Next
    INDEX
    Explanations

    terminology related to blood transfusions and cell transplants

    oai_token-act-pair · gemini-2.0-flash

    blood cells, medical research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     '/',
    -0.49
    orcid
    -0.47
    gehenden
    -0.45
    fhir
    -0.45
    "/",
    -0.44
     '/';
    -0.44
    tableWidget
    -0.42
     ['',
    -0.42
    AccessorTable
    -0.42
     camioneta
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.66
    ::::::::
    0.56
    TagMode
    0.52
     GenerationType
    0.52
    Personendaten
    0.52
     createSlice
    0.50
     snippetHide
    0.49
    ✨:
    0.49
     laid
    0.48
    RectangleBorder
    0.48
    Activations Density 3.610%

    No Known Activations