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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10474
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatment and the need to see a doctor

    oai_token-act-pair · gemini-2.0-flash

    health, legal matters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     sooner
    -0.70
    Soon
    -0.69
     Soon
    -0.67
     soon
    -0.67
    soon
    -0.65
     indisponible
    -0.65
    Autoritní
    -0.63
     nôtre
    -0.63
    posedge
    -0.59
     faſt
    -0.59
    POSITIVE LOGITS
     as
    1.39
     As
    0.75
     как
    0.73
    as
    0.71
     AS
    0.59
    TintMode
    0.59
    As
    0.57
    ChildIndex
    0.56
     як
    0.56
    WebVitals
    0.53
    Activations Density 1.314%

    No Known Activations