© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11352
    Prev
    Next
    INDEX
    Explanations

    digital object identifiers (DOI) and URLs to scientific publications

    oai_token-act-pair · gemini-2.0-flash

    /

    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
    BeginContext
    -0.86
     myſelf
    -0.80
     Meksiku
    -0.80
    astéroïdes
    -0.77
     Efq
    -0.77
     itſelf
    -0.77
     fubject
    -0.73
    ^(@)
    -0.72
     pleaſure
    -0.71
    CodedInputStream
    -0.70
    POSITIVE LOGITS
    UnusedPrivate
    0.67
     navidad
    0.52
    ★
    0.48
     I
    0.47
     A
    0.46
     J
    0.43
     III
    0.43
     S
    0.43
    toPromise
    0.42
    I
    0.41
    Activations Density 3.337%

    No Known Activations