© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1817
    Prev
    Next
    INDEX
    Explanations

    code-related terms like "register", "UIRemoteNotificationType", and "define"

    oai_token-act-pair · gemini-2.0-flash

    Code, 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    oro
    -0.46
     Walters
    -0.41
     Ma
    -0.41
     CH
    -0.41
    al
    -0.41
     C
    -0.40
     P
    -0.40
     Burns
    -0.39
     Ar
    -0.39
     D
    -0.39
    POSITIVE LOGITS
    ConstraintMaker
    0.69
    AccessorTable
    0.65
    EndInit
    0.62
    ContentAsync
    0.62
    ChildScrollView
    0.59
    CloseOperation
    0.59
    adpleegd
    0.59
    PropertyChanging
    0.58
     CreateTagHelper
    0.57
    StructEnd
    0.56
    Activations Density 9.398%

    No Known Activations