© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9225
    Prev
    Next
    INDEX
    Explanations

    text related to event descriptions and historical accounts

    oai_token-act-pair · gemini-2.0-flash

    anniversaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.73
     Bioaccumulative
    -0.71
     himo
    -0.69
    JsonHelper
    -0.68
    tonode
    -0.66
     AssemblyCulture
    -0.66
     betweenstory
    -0.66
     ostavi
    -0.65
     defaultstate
    -0.64
    __(/*!
    -0.64
    POSITIVE LOGITS
     enää
    0.54
    ContentAsync
    0.45
     kuiten
    0.44
    
    0.41
     menschliche
    0.38
    testens
    0.38
    的人都
    0.37
    feinander
    0.37
    _
    0.37
    taught
    0.36
    Activations Density 1.007%

    No Known Activations