© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11570
    Prev
    Next
    INDEX
    Explanations

    language related to risk and problems for the public

    oai_token-act-pair · gemini-2.0-flash

    health-related terms

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

    health

    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
    getMenuInflater
    -0.63
    createCanvas
    -0.56
    findpost
    -0.56
    ControllerTest
    -0.54
    }{*}{
    -0.54
    XmlAccessType
    -0.52
     Kild
    -0.52
    rhosis
    -0.51
    BufferException
    -0.51
    springframework
    -0.50
    POSITIVE LOGITS
     health
    0.74
    Health
    0.69
     Health
    0.65
    health
    0.60
    HEALTH
    0.59
     HEALTH
    0.58
     eyes
    0.57
     sanitaires
    0.56
     sanitaire
    0.55
     Eyes
    0.55
    Activations Density 1.679%

    No Known Activations