© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9404
    Prev
    Next
    INDEX
    Explanations

    network protocol related terms

    oai_token-act-pair · gemini-2.0-flash

    programming/technical code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     DS
    -1.09
     DP
    -1.08
     DA
    -1.06
     DW
    -1.05
     DD
    -1.05
    DW
    -1.03
     DM
    -1.02
     DT
    -1.02
     DH
    -1.02
     DF
    -1.02
    POSITIVE LOGITS
    UnsafeEnabled
    0.47
    SequentialGroup
    0.46
     resourceCulture
    0.44
    MLLoader
    0.41
    ArrowToggle
    0.40
    SpringRunner
    0.39
     препратки
    0.37
     المعيارى
    0.36
    AddHtmlAttribute
    0.34
    MarshalTo
    0.34
    Activations Density 2.677%

    No Known Activations