© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9686
    Prev
    Next
    INDEX
    Explanations

    positive statements about tools, methods, or diagnoses

    oai_token-act-pair · gemini-2.0-flash

    tool

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     defaultstate
    -0.57
    setViewportView
    -0.52
    ínsula
    -0.51
     الحره
    -0.51
    orari
    -0.49
    pă
    -0.49
    msgTypes
    -0.48
     résistant
    -0.47
    hoga
    -0.47
    estacks
    -0.47
    POSITIVE LOGITS
     tools
    1.92
     tool
    1.82
    tool
    1.66
    tools
    1.65
     Tools
    1.64
     TOOLS
    1.58
     Tool
    1.55
    Tool
    1.52
    Tools
    1.52
     TOOL
    1.49
    Activations Density 1.428%

    No Known Activations