Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12322
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences that discuss studies and research and how to improve them

    oai_token-act-pair · gemini-2.0-flash

    research

    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
    WebVitals
    -0.82
    oneofs
    -0.80
    AddTagHelper
    -0.79
     виправивши
    -0.74
    aarrggbb
    -0.72
    MigrationBuilder
    -0.71
    Controllo
    -0.68
     Мексичка
    -0.68
     Chwiliwch
    -0.68
    QMetaType
    -0.67
    POSITIVE LOGITS
    elsif
    0.46
     elif
    0.45
     poved
    0.44
    tał
    0.41
     considérer
    0.40
    ừng
    0.40
    ക്ക
    0.39
     ≠
    0.39
    elif
    0.38
    elseif
    0.38
    Activations Density 2.291%

    No Known Activations