© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2105
    Prev
    Next
    INDEX
    Explanations

    Javascript code snippets with AJAX POST requests

    oai_token-act-pair · gemini-2.0-flash

    Code, scripts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    TypedDataSet
    -0.57
     protoimpl
    -0.54
    tagHelperRunner
    -0.54
     NUKAT
    -0.54
    IonicModule
    -0.53
    setVerticalGroup
    -0.53
    ophyll
    -0.52
    +(\
    -0.52
    IVED
    -0.52
    WireFormat
    -0.52
    POSITIVE LOGITS
    setContentType
    0.48
    dataType
    0.48
    LayoutStyle
    0.47
    zieży
    0.43
    Uninitialized
    0.43
    λευ
    0.42
    ainte
    0.41
    ölcs
    0.41
    packt
    0.41
     atividade
    0.41
    Activations Density 0.811%

    No Known Activations