© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8327
    Prev
    Next
    INDEX
    Explanations

    the word "matters"

    oai_token-act-pair · gemini-2.0-flash

    matters

    np_max-act · gemini-2.0-flash

    matters

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     avoient
    -1.26
     ainfi
    -1.23
     feroit
    -1.18
     purpoſe
    -1.18
     enfans
    -1.17
     étoient
    -1.17
     pleaſure
    -1.13
     ſtate
    -1.11
     reaſon
    -1.09
     chrétien
    -1.09
    POSITIVE LOGITS
    ↵↵
    1.02
     
    0.78
     '
    0.73
    ↵
    0.72
    s
    0.67
     Ben
    0.64
     "
    0.63
    awtextra
    0.63
     No
    0.63
     and
    0.62
    Activations Density 1.517%

    No Known Activations