© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2079
    Prev
    Next
    INDEX
    Explanations

    acronyms with the letters "IS", "IN", "AN", "PR" within them

    oai_token-act-pair · gemini-2.0-flash

    document elements and metadata references

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

    scientific research

    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
    S
    -1.20
     S
    -0.59
     visuales
    -0.56
    ulement
    -0.55
    SQU
    -0.54
    mites
    -0.54
     visualización
    -0.53
     udaler
    -0.52
     mínimos
    -0.52
    vanou
    -0.50
    POSITIVE LOGITS
    脚注の使い方
    0.65
     للمعارف
    0.61
    WebVitals
    0.58
     springfox
    0.57
    Espèce
    0.57
     متعلقه
    0.57
    RunAsync
    0.55
    MeasureSpec
    0.54
     виправивши
    0.54
    AndEndTag
    0.54
    Activations Density 1.488%

    No Known Activations