© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11593
    Prev
    Next
    INDEX
    Explanations

    words implying loss, destruction, or being without

    oai_token-act-pair · gemini-2.0-flash

    negative occurrences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     تضيفلها
    -0.52
    ThroughAttribute
    -0.51
    сме
    -0.48
     censi
    -0.47
     désolés
    -0.47
    ьаж
    -0.44
    RTLD
    -0.44
    foglio
    -0.44
     newOwner
    -0.43
    unus
    -0.43
    POSITIVE LOGITS
     surla
    0.63
    ReusableCell
    0.61
     виправивши
    0.60
     Exacts
    0.59
     deepening
    0.58
     darken
    0.57
     darkening
    0.57
    richTextPanel
    0.57
     downvotes
    0.57
     Cutler
    0.54
    Activations Density 3.262%

    No Known Activations