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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13659
    Prev
    Next
    INDEX
    Explanations

    locations

    oai_token-act-pair · gemini-2.0-flash

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     corpor
    -0.38
    幕
    -0.37
    igraf
    -0.36
     tu
    -0.35
    undidad
    -0.35
    рома
    -0.34
    eding
    -0.34
     medic
    -0.33
    *{
    -0.33
    不清
    -0.33
    POSITIVE LOGITS
     propOrder
    1.07
    ]--;
    0.80
    AntiForgeryToken
    0.77
    aarrggbb
    0.76
    StructEnd
    0.75
    ValueStyle
    0.75
    PyExc
    0.75
    WithIOException
    0.74
     ProtoMessage
    0.74
     <",
    0.73
    Activations Density 0.762%

    No Known Activations