© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8634
    Prev
    Next
    INDEX
    Explanations

    questions or ways to ask for something, and certain punctuation

    oai_token-act-pair · gemini-2.0-flash

    asking 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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    QMetaType
    -0.85
    MLLoader
    -0.68
    loài
    -0.67
    ReusableCell
    -0.63
    }()
    -0.52
     CanadaChoose
    -0.52
    Demografía
    -0.52
    ()],
    -0.52
    twimg
    -0.50
    XmlAccessType
    -0.50
    POSITIVE LOGITS
     how
    2.45
     How
    1.99
    How
    1.95
    how
    1.88
    HOW
    1.59
     HOW
    1.58
     cómo
    1.45
     bagaimana
    1.40
    如何
    1.34
     hvordan
    1.31
    Activations Density 1.406%

    No Known Activations