© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2852
    Prev
    Next
    INDEX
    Explanations

    dates and numbers.

    oai_token-act-pair · gemini-2.0-flash

    Dates and years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    WebVitals
    -0.54
    0
    -0.53
    IntoConstraints
    -0.52
    SpringBootTest
    -0.51
     propOrder
    -0.49
    tagHelperRunner
    -0.48
    2
    -0.47
    請繼續往下閱讀
    -0.47
     (<
    -0.47
    AnimationsModule
    -0.47
    POSITIVE LOGITS
    oaks
    0.64
    domésticos
    0.64
    raits
    0.64
    ukkah
    0.63
    ACTS
    0.59
    melons
    0.58
    Brainz
    0.58
    ptonshire
    0.57
     tetrachloride
    0.57
    urgy
    0.57
    Activations Density 15.868%

    No Known Activations