© 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. 8724
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Holy", and particularly the phrase "Holy Roman"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'Holy'

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

    holy

    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
    webElementGuid
    -0.74
     nakalista
    -0.73
    contentLoaded
    -0.71
    Datuak
    -0.65
     mouseY
    -0.64
    VIAF
    -0.60
    AndEndTag
    -0.60
    RRect
    -0.59
    matchCondition
    -0.59
    AutoScaleMode
    -0.57
    POSITIVE LOGITS
    stretchr
    0.52
    ijski
    0.50
    allage
    0.49
    اقة
    0.46
    gebung
    0.46
    oupe
    0.45
    rood
    0.43
    fassung
    0.43
     ddelweddau
    0.42
     Vielen
    0.42
    Activations Density 0.519%

    No Known Activations