© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10605
    Prev
    Next
    INDEX
    Explanations

    code-related terms like "core", "python", "component"

    oai_token-act-pair · gemini-2.0-flash

    core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    GEBURTSDATUM
    -0.94
    ValueStyle
    -0.81
     виправивши
    -0.75
     nakalista
    -0.71
    rungsseite
    -0.70
    sizeCache
    -0.67
     ExecuteAsync
    -0.65
     ModelExpression
    -0.64
    Chham
    -0.64
    ✨:
    -0.63
    POSITIVE LOGITS
     getopt
    0.63
    CWE
    0.57
    iatric
    0.52
    Forth
    0.50
    djangoproject
    0.48
    CSU
    0.48
    breviation
    0.47
    anny
    0.46
    strerror
    0.45
    ngrx
    0.45
    Activations Density 0.407%

    No Known Activations