© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11967
    Prev
    Next
    INDEX
    Explanations

    words and short sentences that ask questions

    oai_token-act-pair · gemini-2.0-flash

    specific coding or programming language terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     avancé
    -0.52
    bewerken
    -0.49
    adaptiveStyles
    -0.48
    BuilderFactory
    -0.46
     HÀ
    -0.45
    кви
    -0.45
    dotenv
    -0.45
     fallu
    -0.45
     livré
    -0.44
     mémor
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.62
    Distribución
    0.60
     cherchés
    0.57
    ">—
    0.55
    intendent
    0.55
    !*\
    0.55
    itettura
    0.52
    trous
    0.52
    UserScript
    0.52
    columnName
    0.51
    Activations Density 9.226%

    No Known Activations