© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2814
    Prev
    Next
    INDEX
    Explanations

    phrases referring to single payments or financial costs/donations

    oai_token-act-pair · gemini-2.0-flash

    references to "one" and "time"

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

    time and one

    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
    RenderAtEndOf
    -0.94
    reactstrap
    -0.85
    EndInit
    -0.84
    UnusedPrivate
    -0.75
    httphttps
    -0.74
    Diwedd
    -0.71
     يتيمه
    -0.71
     surla
    -0.70
    setupUi
    -0.69
     Jefus
    -0.68
    POSITIVE LOGITS
    time
    1.13
    One
    1.05
    Time
    1.00
     time
    0.99
     One
    0.99
     one
    0.94
    one
    0.92
    off
    0.91
     Time
    0.86
    TIME
    0.85
    Activations Density 1.108%

    No Known Activations