Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5773
    Prev
    Next
    INDEX
    Explanations

    references to armies, countries involved with the soviet union or united states, and time periods

    oai_token-act-pair · gemini-2.0-flash

    terms related to occupations

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

    occupation

    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
    يكب
    -0.66
    setImageBitmap
    -0.59
     atof
    -0.54
    ัง
    -0.53
    DoubleQuotes
    -0.50
    issauga
    -0.49
    Liability
    -0.49
    rites
    -0.49
     twill
    -0.49
     teint
    -0.49
    POSITIVE LOGITS
     occupation
    0.65
    adpleegd
    0.53
     occupy
    0.52
     pac
    0.52
     Occupation
    0.52
     Occup
    0.51
    occupation
    0.51
     occupies
    0.50
     occupying
    0.50
     transférez
    0.50
    Activations Density 3.879%

    No Known Activations