© 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. 10450
    Prev
    Next
    INDEX
    Explanations

    code, programming languages, and programming concepts

    oai_token-act-pair · gemini-2.0-flash

    code, types and protocols

    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
    Process
    -0.39
    ke
    -0.36
    l
    -0.35
    process
    -0.35
    cur
    -0.35
    Properties
    -0.34
    ve
    -0.33
    Ke
    -0.32
    Kee
    -0.32
    утбо
    -0.31
    POSITIVE LOGITS
    ########.
    1.13
     GenerationType
    0.97
    DockStyle
    0.91
     propOrder
    0.91
     ujednoznacz
    0.90
    TagMode
    0.89
     Мексичка
    0.87
    InjectAttribute
    0.87
     дописавши
    0.86
     chi̍t
    0.85
    Activations Density 12.718%

    No Known Activations