© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11673
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to file management or remote code repository commands and operations.

    oai_token-act-pair · gemini-2.0-flash

    File management and coding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     file
    -2.63
     files
    -2.53
     File
    -2.48
     Files
    -2.39
     FILE
    -2.34
    file
    -2.30
    File
    -2.23
    FILE
    -2.14
     FILES
    -2.13
    Files
    -2.11
    POSITIVE LOGITS
    ?}",
    0.37
    はじめに
    0.34
     consultato
    0.33
     الاطلاع
    0.33
     أعلام
    0.33
    SuppressWarnings
    0.32
    astricht
    0.32
     interesan
    0.32
    ureusement
    0.31
    jącego
    0.30
    Activations Density 1.643%

    No Known Activations