© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6239
    Prev
    Next
    INDEX
    Explanations

    references to research papers or external sources, often indicated by bracketed numbers

    oai_token-act-pair · gemini-2.0-flash

    technical document elements or references

    np_token-act-pair-logits · gpt-4o-mini

    citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ninth
    -0.76
     Ninth
    -0.76
     ninety
    -0.75
    9
    -0.67
     Ninety
    -0.65
    ９
    -0.64
    第九
    -0.63
     nine
    -0.62
     September
    -0.62
     Nine
    -0.61
    POSITIVE LOGITS
    SequentialGroup
    0.59
    ugc
    0.59
     Autorizaciones
    0.58
    BufferException
    0.57
    usercontent
    0.54
    iStock
    0.48
    Establishing
    0.48
     Establishing
    0.47
    DoubleQuotes
    0.46
    scalatest
    0.46
    Activations Density 2.827%

    No Known Activations