© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10570
    Prev
    Next
    INDEX
    Explanations

    parts of code, specifically PHP code using the Nginx web server API

    oai_token-act-pair · gemini-2.0-flash

    words or patterns suggesting object or function identifiers

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

    plus sign

    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
    Билгалдахарш
    -0.82
    <bos>
    -0.81
     صوتيه
    -0.76
    AsUp
    -0.76
    ]")]
    -0.75
     ivelany
    -0.75
     internetowa
    -0.71
     Wiktionnaire
    -0.71
     '\\;'
    -0.71
     AssemblyProduct
    -0.69
    POSITIVE LOGITS
    ÁT
    0.52
     Bep
    0.52
    ropa
    0.50
    EMOS
    0.49
    rative
    0.47
    tive
    0.47
    arf
    0.45
    вість
    0.44
    enk
    0.44
    object
    0.43
    Activations Density 5.516%

    No Known Activations