© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    technical language related to transistors and semiconductor devices

    oai_token-act-pair · gemini-2.0-flash

    prefixes or terms related to technology or materials

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

    Semiconductor devices

    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
     للمعارف
    -0.95
    IsContent
    -0.72
    ')")
    -0.66
    UserScript
    -0.64
      (
    -0.64
    lusconi
    -0.63
    endphp
    -0.63
    VersionUID
    -0.63
     sauvages
    -0.63
     Theſe
    -0.63
    POSITIVE LOGITS
    oa̍t
    0.52
    uls
    0.49
    chul
    0.44
    ulp
    0.44
    ul
    0.42
     trans
    0.42
    Пол
    0.42
     Ul
    0.41
    bo
    0.39
     re
    0.39
    Activations Density 3.377%

    No Known Activations