© 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. 1000
    Prev
    Next
    INDEX
    Explanations

    places as belonging to companies

    oai_token-act-pair · gemini-2.0-flash

    Titles and positions

    np_max-act-logits · 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
    WireFormatLite
    -0.74
    :✨
    -0.65
    ########.
    -0.65
     CreateTagHelper
    -0.64
    ValueStyle
    -0.62
    CreateModel
    -0.60
    expandindo
    -0.60
    SOUNDBITE
    -0.58
    SelectedIndex
    -0.56
    DeleteBehavior
    -0.56
    POSITIVE LOGITS
    Geplaatst
    0.48
     thập
    0.46
    ident
    0.46
    Життєпис
    0.44
    </thead>
    0.43
    prop
    0.42
    ВД
    0.42
    httphttps
    0.41
    談社
    0.41
    mäßig
    0.41
    Activations Density 2.599%

    No Known Activations