© 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. 3590
    Prev
    Next
    INDEX
    Explanations

    terms related to genetics and biological engineering

    oai_token-act-pair · gemini-2.0-flash

    technology and terms related to genetics

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

    genetic

    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
     bone
    -0.71
    bone
    -0.70
    Bone
    -0.62
     huesos
    -0.61
     Bone
    -0.61
     cref
    -0.57
    ğraf
    -0.56
    Datuak
    -0.56
    BONE
    -0.53
    parsedMessage
    -0.53
    POSITIVE LOGITS
    WebServlet
    0.76
    resave
    0.57
    Express
    0.48
    SafeMath
    0.48
    oa̍t
    0.48
    MultipartFile
    0.47
    Sklici
    0.47
     Express
    0.47
     chow
    0.46
     Tink
    0.46
    Activations Density 1.632%

    No Known Activations