© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6718
    Prev
    Next
    INDEX
    Explanations

    the string "baz" or similarly structured names with those letters

    oai_token-act-pair · gemini-2.0-flash

    Code snippets and uncommon words

    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
    __((
    -0.42
    azin
    -0.41
    especie
    -0.39
    tslib
    -0.39
    msgTypes
    -0.38
     ready
    -0.37
    リート
    -0.37
    ftime
    -0.37
    writeField
    -0.36
     успеха
    -0.36
    POSITIVE LOGITS
    ьаж
    0.72
     &___
    0.71
     autorytatywna
    0.68
    ništ
    0.66
    makeText
    0.66
     переписи
    0.64
     Numerade
    0.62
    astéroïdes
    0.60
    limsy
    0.58
     Catawiki
    0.58
    Activations Density 0.270%

    No Known Activations