© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9936
    Prev
    Next
    INDEX
    Explanations

    snippets of code, particularly java servlets.

    oai_token-act-pair · gemini-2.0-flash

    non-standard programming methods or tags

    np_token-act-pair-logits · gpt-4o-mini

    Java web applications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ChildScrollView
    -0.49
    PagerAdapter
    -0.48
     Geraadpleegd
    -0.47
     immortality
    -0.44
     meia
    -0.43
    providedIn
    -0.43
     Primaria
    -0.42
    匠
    -0.42
     TableColumn
    -0.42
    chine
    -0.40
    POSITIVE LOGITS
     Infórmanos
    0.76
    AndEndTag
    0.70
     transfieras
    0.66
    RequestBuilder
    0.65
    InjectAttribute
    0.65
    windowFixed
    0.60
    WriteTagHelper
    0.59
    ########.
    0.59
    onha
    0.58
    čenje
    0.55
    Activations Density 0.629%

    No Known Activations