© 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. 9307
    Prev
    Next
    INDEX
    Explanations

    code, specifically code related to API calls and REST

    oai_token-act-pair · gemini-2.0-flash

    Code and Azure networking

    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
    UpInside
    -0.68
    xase
    -0.62
    ItemBackground
    -0.61
    SharedDtor
    -0.60
     dAtA
    -0.60
    Enllaces
    -0.58
    曖昧さ回避
    -0.58
     onOptions
    -0.57
    UnsafeEnabled
    -0.57
     вікі
    -0.56
    POSITIVE LOGITS
     Référence
    0.54
    tagHelperRunner
    0.51
    BeginContext
    0.45
    |}{}
    0.41
     något
    0.41
    クタイ
    0.40
     ?:
    0.40
    之
    0.40
    คา
    0.40
    ätä
    0.40
    Activations Density 3.033%

    No Known Activations