© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10438
    Prev
    Next
    INDEX
    Explanations

    words or phrases mentioning the frequency of events

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ]--;
    -0.64
    permitAll
    -0.63
    ReusableCell
    -0.63
    setupUi
    -0.60
     writeTo
    -0.60
     sucul
    -0.59
    Hentet
    -0.57
    iarkan
    -0.57
    continued
    -0.56
     foreach
    -0.56
    POSITIVE LOGITS
     sometimes
    1.27
     often
    1.26
    Sometimes
    1.17
     Sometimes
    1.15
    sometimes
    1.11
     oftentimes
    1.09
    often
    1.09
     Often
    1.08
    Often
    1.05
    chmal
    1.01
    Activations Density 0.837%

    No Known Activations