© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3828
    Prev
    Next
    INDEX
    Explanations

    text discussing chemical bonds or materials science

    oai_token-act-pair · gemini-2.0-flash

    hydrogen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ########.
    -0.60
     gewor
    -0.57
     Nez
    -0.54
     malice
    -0.52
    avyzd
    -0.52
    unga
    -0.50
     عزی
    -0.49
    aimer
    -0.49
    例句
    -0.49
     SIC
    -0.48
    POSITIVE LOGITS
     hydrogen
    0.88
     Wasserstoff
    0.75
     Hydrogen
    0.73
    Hydrogen
    0.71
    hydrogen
    0.68
    ///</
    0.65
    氢
    0.61
     Mina
    0.55
    XmlType
    0.55
    NameInMap
    0.55
    Activations Density 2.430%

    No Known Activations