© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12792
    Prev
    Next
    INDEX
    Explanations

    words related to physical structure and location within it

    oai_token-act-pair · gemini-2.0-flash

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     top
    -1.08
    Top
    -0.95
    TOP
    -0.91
     Top
    -0.91
     toppen
    -0.90
    top
    -0.86
     TOP
    -0.85
     upper
    -0.82
    Upper
    -0.71
     сверху
    -0.69
    POSITIVE LOGITS
    LocalizedString
    0.73
     NSCoder
    0.54
    ânsito
    0.54
    marshaller
    0.52
    DIPSETTING
    0.50
    utilisons
    0.48
     succeeded
    0.47
    ETIME
    0.47
    发表于
    0.47
     bile
    0.47
    Activations Density 7.865%

    No Known Activations