© 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. 10424
    Prev
    Next
    INDEX
    Explanations

    measurement parameters such as percent, levels, concentrations, normalized, etc

    oai_token-act-pair · gemini-2.0-flash

    percent/percentage

    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
     kasarigan
    -0.98
    RenderAtEndOf
    -0.98
     CreateTagHelper
    -0.91
     autorytatywna
    -0.83
     المعيارى
    -0.79
    abestanden
    -0.76
     виправивши
    -0.74
     Chwiliwch
    -0.74
     nahilalakip
    -0.73
    webElementXpaths
    -0.73
    POSITIVE LOGITS
    #
    0.52
    netbeans
    0.50
     difference
    0.48
    gypte
    0.47
    %
    0.46
     pourcentage
    0.44
     upon
    0.43
    ~
    0.43
    ss
    0.43
     comparing
    0.42
    Activations Density 3.000%

    No Known Activations