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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12114
    Prev
    Next
    INDEX
    Explanations

    words or phrases that follow the word "and"

    oai_token-act-pair · gemini-2.0-flash

    Understanding after a period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    archiviato
    -0.70
    DebuggerStep
    -0.59
    OGND
    -0.58
    ρους
    -0.57
    AutoField
    -0.54
    GRANTED
    -0.53
    Портал
    -0.52
    theless
    -0.52
     PMID
    -0.52
    AndEndTag
    -0.52
    POSITIVE LOGITS
    RefreshLayout
    0.54
    setupUi
    0.50
    AxisAlignment
    0.47
    MessageTagHelper
    0.47
    可惜
    0.45
     each
    0.45
     xong
    0.44
    irmed
    0.44
     depending
    0.44
     yet
    0.43
    Activations Density 2.412%

    No Known Activations