© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7942
    Prev
    Next
    INDEX
    Explanations

    passages discussing HIV/AIDS research, prevention, or treatment.

    oai_token-act-pair · gemini-2.0-flash

    HIV

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    InjectAttribute
    -0.84
    /**
    -0.81
    __(/*!
    -0.81
    Искәрмәләр
    -0.79
    JspWriter
    -0.78
    хьтан
    -0.78
    脚注の使い方
    -0.77
    ContentAsync
    -0.75
     يتيمه
    -0.74
    DebuggerNonUser
    -0.72
    POSITIVE LOGITS
     faces
    0.55
     FACE
    0.51
     face
    0.51
     Face
    0.51
     career
    0.46
     Page
    0.45
    FACE
    0.45
     Career
    0.45
    face
    0.45
    Face
    0.45
    Activations Density 14.442%

    No Known Activations