© 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. 15058
    Prev
    Next
    INDEX
    Explanations

    a variety of delimiters, symbols, and structural patterns common in code and data formats.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     AssemblyCulture
    -0.58
    TagHelper
    -0.55
     оригіналу
    -0.54
     تانيه
    -0.54
    новништво
    -0.54
    Personensuche
    -0.53
    TypedDataSet
    -0.52
     CreateTagHelper
    -0.51
    drawSprites
    -0.50
     hoofd
    -0.49
    POSITIVE LOGITS
    titleMargin
    0.62
     internetowa
    0.58
    nologies
    0.57
     ExecuteAsync
    0.55
     chargeur
    0.53
    SWR
    0.53
     kait
    0.52
    CHOR
    0.52
     FRAG
    0.52
    }`}>
    0.52
    Activations Density 9.378%

    No Known Activations