© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6681
    Prev
    Next
    INDEX
    Explanations

    words that appear in website source code

    oai_token-act-pair · gemini-2.0-flash

    Computer science/mathematics text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ########.
    -1.12
     utafitiHapana
    -1.05
     initComponents
    -1.04
     تضيفلها
    -0.99
    ⓧ
    -0.93
    awtextra
    -0.92
    WithIOException
    -0.91
     متعلقه
    -0.88
    RegressionTest
    -0.88
    ViewFeatures
    -0.87
    POSITIVE LOGITS
    اظ
    0.39
    -
    0.39
     B
    0.39
    Com
    0.38
    已
    0.38
     C
    0.37
    as
    0.36
     spring
    0.35
    í
    0.35
    ir
    0.35
    Activations Density 3.298%

    No Known Activations