© 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. 13755
    Prev
    Next
    INDEX
    Explanations

    terms found in code, such as variables or commands

    oai_token-act-pair · gemini-2.0-flash

    programming

    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
    EndContext
    -0.66
    WriteTagHelper
    -0.62
    katapos
    -0.61
    icolon
    -0.60
    termilk
    -0.59
    ANTAGES
    -0.59
    Sedangkan
    -0.59
    persky
    -0.58
    prnewswire
    -0.58
    corns
    -0.58
    POSITIVE LOGITS
      
    0.50
    $\\
    0.46
    :✨
    0.45
    dios
    0.45
    IsContent
    0.43
    eno
    0.42
     SUDOC
    0.42
     caps
    0.42
    tai
    0.41
     sol
    0.41
    Activations Density 2.523%

    No Known Activations