© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14091
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to development/construction and the healthcare industry

    oai_token-act-pair · gemini-2.0-flash

    terms related to aviation and healthcare

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

    healthcare or housing

    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
    تقاوى
    -0.76
    曖昧さ回避
    -0.58
     препратки
    -0.55
     astore
    -0.54
    Hentet
    -0.54
    UrlResolution
    -0.53
    참고
    -0.52
    glLoadIdentity
    -0.52
    findpost
    -0.52
    verwijspagina
    -0.52
    POSITIVE LOGITS
    DebuggerStep
    0.61
    oscopy
    0.60
    MENAFN
    0.58
     recession
    0.57
     autorità
    0.57
     eventType
    0.55
    InputTagHelper
    0.54
    authorities
    0.54
     safety
    0.54
     Revenue
    0.54
    Activations Density 1.834%

    No Known Activations