© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10787
    Prev
    Next
    INDEX
    Explanations

    references to file paths in shell scripts

    oai_token-act-pair · gemini-2.0-flash

    code and computing environments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ########.
    -0.65
    profen
    -0.57
    getItemId
    -0.57
    InjectAttribute
    -0.56
     تضيفلها
    -0.55
    soft
    -0.55
    Affirmed
    -0.55
    RTGC
    -0.55
     समीक्षक
    -0.55
     memoized
    -0.55
    POSITIVE LOGITS
     air
    0.55
    RegressionTest
    0.49
    stdc
    0.48
     ambient
    0.46
    setWindow
    0.45
     Gegens
    0.45
     omge
    0.44
    AndroidJUnit
    0.43
     environment
    0.43
    Environmental
    0.43
    Activations Density 2.443%

    No Known Activations