© 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. 10596
    Prev
    Next
    INDEX
    Explanations

    mentions of epilepsy, seizures and anti-epileptic medication, especially in connection with BECTS and children.

    oai_token-act-pair · gemini-2.0-flash

    "ep" words

    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
     AssemblyProduct
    -0.59
    PullParser
    -0.57
    CrossRef
    -0.56
    alleros
    -0.53
     AssemblyTitle
    -0.52
    الإنجليزية
    -0.52
    ("}\
    -0.52
    enderror
    -0.51
    SharedDtor
    -0.50
    ాన
    -0.49
    POSITIVE LOGITS
     getItemId
    0.60
    ep
    0.56
     epi
    0.55
     Serap
    0.54
     grand
    0.52
    epi
    0.51
    ieh
    0.50
    ReusableCell
    0.50
    Ep
    0.49
     ep
    0.49
    Activations Density 2.446%

    No Known Activations