© 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. 8227
    Prev
    Next
    INDEX
    Explanations

    either the word "foreach" or some word containing the substring "war"

    oai_token-act-pair · gemini-2.0-flash

    foreach

    np_max-act · gemini-2.0-flash
    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
     Púb
    -0.71
     Gallimard
    -0.65
    sometimes
    -0.64
     produisent
    -0.63
     crainte
    -0.62
     juges
    -0.62
     Ancona
    -0.62
    RemoteException
    -0.61
    Sometimes
    -0.60
     eccell
    -0.60
    POSITIVE LOGITS
    æa
    0.68
     autorytatywna
    0.68
    hubanes
    0.65
    SpringBootTest
    0.64
     BoxDecoration
    0.63
    _"+
    0.61
    цездатний
    0.60
    "}")
    0.60
    chastic
    0.60
     تضيفلها
    0.60
    Activations Density 0.086%

    No Known Activations