© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11495
    Prev
    Next
    INDEX
    Explanations

    code

    oai_token-act-pair · gemini-2.0-flash

    code-related terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     inne
    -0.32
    ราช
    -0.29
    倍
    -0.27
     nào
    -0.25
    Ca
    -0.25
     senare
    -0.25
    矶
    -0.24
     disques
    -0.24
    Double
    -0.23
     чи
    -0.23
    POSITIVE LOGITS
    enumi
    1.08
     CreateTagHelper
    1.00
     &___
    0.99
    SharedCtor
    0.95
     kasarigan
    0.94
    AddTagHelper
    0.93
    InstrumentedTest
    0.91
     myſelf
    0.88
    AntiForgeryToken
    0.88
     Monfieur
    0.87
    Activations Density 0.363%

    No Known Activations