© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7646
    Prev
    Next
    INDEX
    Explanations

    the word "train."

    oai_token-act-pair · gemini-2.0-flash

    train

    np_max-act · gemini-2.0-flash

    train

    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
    ,
    -1.22
    .
    -1.09
    /
    -0.81
    -
    -0.81
     and
    -0.75
     the
    -0.74
    _
    -0.73
    0
    -0.73
    3
    -0.70
    (
    -0.69
    POSITIVE LOGITS
     Theſe
    1.56
     Efq
    1.45
    )";
    
    1.37
     Monfieur
    1.34
     Jefus
    1.34
    )");
    
    1.34
     itſelf
    1.31
     Diſ
    1.31
     themſelves
    1.29
     Reſ
    1.28
    Activations Density 3.944%

    No Known Activations