© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8923
    Prev
    Next
    INDEX
    Explanations

    mentions of branches, roles, and users along with the phrase "per-patient-year"

    oai_token-act-pair · gemini-2.0-flash

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    fortawesome
    -0.54
     Completely
    -0.53
     Totally
    -0.53
    ChildScrollView
    -0.49
     completely
    -0.48
     totally
    -0.48
    aran
    -0.48
     xăm
    -0.47
    tadi
    -0.46
    anu
    -0.46
    POSITIVE LOGITS
    PhysRevD
    0.69
    adpleegd
    0.69
    criminator
    0.68
    parsedMessage
    0.67
    EndInit
    0.66
    ględ
    0.65
    ValueStyle
    0.65
     internetowa
    0.65
    exitRule
    0.65
    رشف
    0.60
    Activations Density 1.184%

    No Known Activations