© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10841
    Prev
    Next
    INDEX
    Explanations

    code-related snippets with keywords such as reading, parsing, building, creating, constructing, writing, and determining.

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ECT
    -0.41
    migrationBuilder
    -0.41
     NIS
    -0.40
     KX
    -0.40
     ERS
    -0.40
    \{\\
    -0.39
     crv
    -0.39
     AFS
    -0.38
     barriga
    -0.38
     stik
    -0.38
    POSITIVE LOGITS
     unknownFields
    0.79
    tagHelper
    0.76
     CreateTagHelper
    0.73
    XmlIgnore
    0.71
     Greenberg
    0.68
     оригіналу
    0.67
    iphery
    0.67
    Enllaces
    0.66
     instanceof
    0.65
    nolia
    0.65
    Activations Density 3.467%

    No Known Activations