© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11954
    Prev
    Next
    INDEX
    Explanations

    web addresses and filepaths, especially those including common domain names or file types

    oai_token-act-pair · gemini-2.0-flash

    programming or tech-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Domain endings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     R
    -0.57
     I
    -0.56
     $\
    -0.48
    ~
    -0.47
    待
    -0.47
    --
    -0.47
    ēm
    -0.47
    лот
    -0.46
     confirmed
    -0.46
    ah
    -0.46
    POSITIVE LOGITS
     ModelExpression
    1.09
     للاسماء
    0.89
    IUrlHelper
    0.88
    Hochspringen
    0.85
    InjectAttribute
    0.78
    "}>
    0.76
    RetentionPolicy
    0.75
     houſe
    0.73
     itſelf
    0.73
     estekak
    0.72
    Activations Density 3.779%

    No Known Activations