© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6765
    Prev
    Next
    INDEX
    Explanations

    the word "internal" (particularly in code) and somewhat also its opposite "external", alongside some words that commonly appear near them.

    oai_token-act-pair · gemini-2.0-flash

    internal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     internal
    -2.66
     Internal
    -2.48
    Internal
    -2.45
    internal
    -2.45
     INTERNAL
    -2.22
     internally
    -2.05
    INTERNAL
    -1.91
     external
    -1.69
     External
    -1.69
    External
    -1.63
    POSITIVE LOGITS
     MainAxisSize
    0.65
     BrowserModule
    0.64
    XmlAccessType
    0.60
    printStackTrace
    0.59
    ynchrotron
    0.59
     متعلقه
    0.58
    
    0.57
    EndGlobalSection
    0.57
    UnknownFieldSet
    0.56
    EndProject
    0.56
    Activations Density 1.784%

    No Known Activations