© 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. 2021
    Prev
    Next
    INDEX
    Explanations

    words and phrases about problems or requests and debit cards

    oai_token-act-pair · gemini-2.0-flash

    programming questions

    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
     habet
    -0.48
    ########.
    -0.47
     eût
    -0.46
     tubeless
    -0.46
     mourut
    -0.46
    amatkan
    -0.45
     offerts
    -0.45
     katze
    -0.45
     alimentaires
    -0.45
     تانيه
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.73
    GUILayout
    0.69
     CURIAM
    0.69
    🏻
    0.68
     />);
    0.68
    Means
    0.67
    ReusableCell
    0.67
    🏼
    0.66
    Referanser
    0.65
    WireFormatLite
    0.65
    Activations Density 10.996%

    No Known Activations