© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15040
    Prev
    Next
    INDEX
    Explanations

    words associated with medical studies involving people, often in the context of eligibility and participation

    oai_token-act-pair · gemini-2.0-flash

    Study inclusion/exclusion criteria

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     qualify
    -2.58
     qualifying
    -2.55
     qualified
    -2.44
     qualification
    -2.28
     qualifies
    -2.20
    qualified
    -2.17
     Qualified
    -2.17
    Qualified
    -2.14
     QUAL
    -2.09
     Qualifying
    -2.08
    POSITIVE LOGITS
     Brest
    0.50
    IMC
    0.47
     برانيه
    0.45
    fficking
    0.44
    IRR
    0.44
    ள்
    0.43
    ➟
    0.43
     Bytes
    0.42
    ışı
    0.42
     торт
    0.42
    Activations Density 3.513%

    No Known Activations