© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3453
    Prev
    Next
    INDEX
    Explanations

    code or code-like syntax, potentially related to data structures or network requests

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or special characters

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

    Code operators

    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
     isoto
    -0.54
    wpi
    -0.54
     #(
    -0.54
    şiv
    -0.54
    BOA
    -0.49
     indiv
    -0.49
     himo
    -0.49
    pat
    -0.49
    stateMutability
    -0.48
    ArgsConstructor
    -0.48
    POSITIVE LOGITS
    TagHelper
    0.56
    )$/,
    0.56
     للمعارف
    0.55
    EndContext
    0.54
    Dislikes
    0.52
     tromper
    0.51
    ULF
    0.50
    ensão
    0.50
     électroniques
    0.50
     precisione
    0.49
    Activations Density 4.251%

    No Known Activations