© 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. 13540
    Prev
    Next
    INDEX
    Explanations

    URLs, especially those ending in ".htm" or containing "index"

    oai_token-act-pair · gemini-2.0-flash

    file extensions and URLs

    np_token-act-pair-logits · gpt-4o-mini
    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
    Datuak
    -0.60
    SBATCH
    -0.58
    vician
    -0.55
     Andromeda
    -0.51
    romeda
    -0.51
     TextEditing
    -0.51
    ⚭
    -0.51
    ,’
    -0.50
     hefyd
    -0.50
    Дереккөздер
    -0.50
    POSITIVE LOGITS
     Roskov
    0.60
    httphttps
    0.59
    cfm
    0.58
    cshtml
    0.58
    php
    0.57
    Chham
    0.56
    html
    0.54
    Fns
    0.54
    TagHelpers
    0.54
    ?>
    0.54
    Activations Density 2.064%

    No Known Activations