© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11258
    Prev
    Next
    INDEX
    Explanations

    verbs and adverbs related to making progress on a task or the state of completion

    oai_token-act-pair · gemini-2.0-flash

    Starting, happening, or failing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     &___
    -0.90
    RectangleBorder
    -0.88
     ویکی‌پدیای
    -0.86
    IntoConstraints
    -0.84
    BeginContext
    -0.80
     Jacobian
    -0.79
    ModelSerializer
    -0.78
     surla
    -0.77
    TintMode
    -0.77
    aarrggbb
    -0.77
    POSITIVE LOGITS
     not
    0.62
     to
    0.59
     able
    0.55
     often
    0.53
     be
    0.52
     likely
    0.51
     never
    0.50
    ารถ
    0.50
     bear
    0.48
     have
    0.48
    Activations Density 1.290%

    No Known Activations