© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10324
    Prev
    Next
    INDEX
    Explanations

    scientific texts about paleontology and botany

    oai_token-act-pair · gemini-2.0-flash

    terms related to display and mounting

    np_token-act-pair-logits · gpt-4o-mini

    display and mount

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    hadores
    -0.48
    styleType
    -0.45
     kul
    -0.44
    ERIE
    -0.44
    Collections
    -0.44
     collectors
    -0.43
    Collect
    -0.43
    cogn
    -0.42
    Viitteet
    -0.42
    strich
    -0.42
    POSITIVE LOGITS
    ьаж
    0.85
     display
    0.79
     mounted
    0.75
     Display
    0.72
     DISPLAY
    0.71
    oredCriteria
    0.71
     mounts
    0.70
     MOUNT
    0.70
    display
    0.68
     mount
    0.68
    Activations Density 2.153%

    No Known Activations