© 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. 16120
    Prev
    Next
    INDEX
    Explanations

    words related to the physical state

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    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
     how
    -0.60
    ThroughAttribute
    -0.59
    VersionUID
    -0.56
    how
    -0.53
    Cuánt
    -0.52
     HOW
    -0.50
    isContained
    -0.50
     How
    -0.50
    HOW
    -0.50
     what
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    0.73
    mybatisplus
    0.69
     nahilalakip
    0.68
    BeginContext
    0.63
     estekak
    0.62
    oredCriteria
    0.61
    ViewImports
    0.59
    tanleria
    0.59
     Италијани
    0.59
     utafitiHapana
    0.58
    Activations Density 5.624%

    No Known Activations