© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11231
    Prev
    Next
    INDEX
    Explanations

    the word "external" when describing a memory access.

    oai_token-act-pair · gemini-2.0-flash

    external

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     external
    -1.72
    external
    -1.63
     External
    -1.59
    External
    -1.51
     EXTERNAL
    -1.25
     externally
    -1.25
     externe
    -1.23
     externa
    -1.15
     exterior
    -1.14
     externo
    -1.14
    POSITIVE LOGITS
    ThroughAttribute
    0.45
    glement
    0.45
    eron
    0.44
     har
    0.44
     o
    0.42
    udere
    0.42
    nesc
    0.41
    text
    0.41
    har
    0.41
    zec
    0.40
    Activations Density 0.662%

    No Known Activations