© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14831
    Prev
    Next
    INDEX
    Explanations

    words within medical texts specifically related to catheters and heart conditions

    oai_token-act-pair · gemini-2.0-flash

    catheters

    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
     Normdatei
    -0.68
    rawDesc
    -0.63
    </thead>
    -0.56
     ***!
    -0.53
     Produits
    -0.50
     autorité
    -0.49
    +#+#
    -0.49
    ChildScrollView
    -0.47
     habet
    -0.46
     Infórmanos
    -0.46
    POSITIVE LOGITS
    RUnlock
    0.57
     Vikipedi
    0.56
    Catégorie
    0.54
    évaluateur
    0.54
    UCTION
    0.53
    rosine
    0.52
    enos
    0.52
    silien
    0.51
    navigationItem
    0.50
    ografija
    0.50
    Activations Density 1.679%

    No Known Activations