© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11188
    Prev
    Next
    INDEX
    Explanations

    words about something being true/real/present

    oai_token-act-pair · gemini-2.0-flash

    existence/action

    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
    Portail
    -0.79
     تضيفلها
    -0.78
     tartalomajánló
    -0.75
     समीक्षाओं
    -0.74
     itſelf
    -0.72
     myſelf
    -0.71
     Commencez
    -0.70
     الدولى
    -0.69
    ChildIndex
    -0.69
     Paglinawan
    -0.69
    POSITIVE LOGITS
    h
    0.46
     h
    0.46
    Xna
    0.46
     Davison
    0.42
     spécifique
    0.42
    ="?
    0.42
     $("<
    0.41
     S
    0.41
    務省
    0.41
    Παραπομπές
    0.41
    Activations Density 0.975%

    No Known Activations