© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4201
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatments and studies, especially those assessing effectiveness

    oai_token-act-pair · gemini-2.0-flash

    medical treatments

    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
     intervention
    -0.73
     Intervention
    -0.72
    Intervention
    -0.71
     Interventions
    -0.67
     interventions
    -0.66
    intervention
    -0.66
     Treatment
    -0.63
     Therapy
    -0.63
     mxArray
    -0.62
    peutic
    -0.61
    POSITIVE LOGITS
    aleg
    0.54
     omission
    0.52
     NUKAT
    0.52
    ứa
    0.49
    ẳn
    0.48
    شة
    0.48
     agré
    0.48
     illiteracy
    0.47
    Vendors
    0.47
    AFFIRMED
    0.47
    Activations Density 9.503%

    No Known Activations