© 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. 11167
    Prev
    Next
    INDEX
    Explanations

    conditional statements expressing opinions or feelings ("if" statements).

    oai_token-act-pair · gemini-2.0-flash

    if

    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
    jš
    -0.56
     vč
    -0.49
     sezione
    -0.49
    shell
    -0.47
    raska
    -0.47
    Shell
    -0.47
    라고
    -0.46
    mort
    -0.46
    zinger
    -0.45
     Wohnen
    -0.45
    POSITIVE LOGITS
    UrlResolution
    0.66
     propOrder
    0.62
     AssemblyProduct
    0.57
     سكانية
    0.56
    kloped
    0.56
     }</
    0.54
    JsonHelper
    0.53
    Koordin
    0.51
     QtWidgets
    0.51
     kasarigan
    0.51
    Activations Density 7.154%

    No Known Activations