© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11756
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gemini-2.0-flash

    text

    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
    subsection
    -0.68
    DeleteBehavior
    -0.62
    (($
    -0.62
    ($
    -0.59
    QMetaType
    -0.57
    =$
    -0.57
     stål
    -0.57
    ∛
    -0.56
    日閲覧
    -0.54
    <h2>
    -0.53
    POSITIVE LOGITS
    eradish
    0.70
     mxArray
    0.69
    »։
    0.69
     ครับ
    0.68
    LOYEES
    0.68
    "):
    0.67
     endblock
    0.67
    [toxicity=0]
    0.67
    ฯ
    0.67
    σμο
    0.66
    Activations Density 1.146%

    No Known Activations