© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3991
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that describe a field of study

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Personendaten
    -1.28
    DockStyle
    -0.98
     estekak
    -0.92
     CreateTagHelper
    -0.87
    ViewFeatures
    -0.85
    RectangleBorder
    -0.85
     MainAxisSize
    -0.81
    GraphicsUnit
    -0.81
    ArgsConstructor
    -0.79
     שוליים
    -0.78
    POSITIVE LOGITS
    <bos>
    0.54
    et
    0.45
    ®
    0.44
    ™
    0.44
     tabletas
    0.44
    *
    0.43
    Qaeda
    0.42
     (
    0.41
     *
    0.40
     Trilogy
    0.40
    Activations Density 6.399%

    No Known Activations