© 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. 6314
    Prev
    Next
    INDEX
    Explanations

    the term "subject"

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

    instances of the word "subject" being used, often in a legal or regulatory context

    oai_token-act-pair · gemini-2.0-flash

    subject

    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
    tvguidetime
    -0.67
     allAfrica
    -0.65
     layui
    -0.62
    queryInterface
    -0.54
    leria
    -0.53
    CopyWith
    -0.52
    abetta
    -0.52
    CrossRef
    -0.51
     gros
    -0.47
     createState
    -0.47
    POSITIVE LOGITS
     matter
    0.67
    matter
    0.61
     étrangère
    0.59
     enfans
    0.58
     ISNI
    0.56
     cromado
    0.54
     endfor
    0.54
     souple
    0.54
     vulga
    0.53
     fijo
    0.53
    Activations Density 6.195%

    No Known Activations