© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 435
    Prev
    Next
    INDEX
    Explanations

    the word "Dark" and the words directly before or after it

    oai_token-act-pair · gemini-2.0-flash

    Dark matter research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    strptime
    -0.60
    Kjelder
    -0.59
    CloseOperation
    -0.56
     مشين
    -0.56
    (;;)
    -0.53
    RemoveField
    -0.51
    bumptech
    -0.50
    DotNetBar
    -0.50
     UITableViewCell
    -0.50
     šķ
    -0.49
    POSITIVE LOGITS
    DoubleQuotes
    0.59
    Rè
    0.54
     gynhyrchwyd
    0.52
    Abit
    0.51
    ensão
    0.49
    side
    0.46
    rangea
    0.46
    pots
    0.46
     infiltrated
    0.46
     Cze
    0.46
    Activations Density 1.630%

    No Known Activations