© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16159
    Prev
    Next
    INDEX
    Explanations

    code snippets, tutorials, and links to documentation

    oai_token-act-pair · gemini-2.0-flash

    tutorial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Попис
    -0.50
    unzione
    -0.50
    Derbyniad
    -0.49
     zvuky
    -0.49
    UnitTesting
    -0.49
     NDEBUG
    -0.47
    mergeFrom
    -0.47
    boarding
    -0.47
    rollers
    -0.47
     externi
    -0.47
    POSITIVE LOGITS
    AsUp
    0.64
     estimés
    0.62
     tips
    0.58
     Infórmanos
    0.57
     typelib
    0.53
     technique
    0.52
     Normdatei
    0.52
     techniques
    0.52
    Пример
    0.50
    ″]
    0.50
    Activations Density 5.384%

    No Known Activations