© 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. 9364
    Prev
    Next
    INDEX
    Explanations

    words related to senior health and mobile applications

    oai_token-act-pair · gemini-2.0-flash

    medical terminology and health-related terms

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

    general text

    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
     مرئيه
    -0.81
    RenderAtEndOf
    -0.79
    AddTagHelper
    -0.74
    antaranya
    -0.71
    XmlAccessorType
    -0.71
     AssemblyVersion
    -0.71
     nahilalakip
    -0.70
     للمعارف
    -0.69
    berdayakan
    -0.66
     doubtnut
    -0.66
    POSITIVE LOGITS
     solely
    0.75
     within
    0.71
     whereas
    0.71
     extra
    0.71
     coronary
    0.68
     excessive
    0.67
     constructing
    0.67
     despatched
    0.66
     cowl
    0.66
     pores
    0.64
    Activations Density 27.452%

    No Known Activations