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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 962
    Prev
    Next
    INDEX
    Explanations

    institutional

    np_max-act-logits · gemini-2.0-flash

    words related to institutions

    oai_token-act-pair · gemini-2.0-flash

    institutional

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    oflavin
    -0.56
    ="#"><
    -0.52
    龄
    -0.47
    CompleteListener
    -0.47
     Ergänzung
    -0.46
     vokal
    -0.46
    anol
    -0.46
    datab
    -0.46
     Fil
    -0.45
    erez
    -0.45
    POSITIVE LOGITS
    .*")]
    0.76
     MainAxisSize
    0.70
     magasiner
    0.58
    ReusableCell
    0.58
    %)$
    0.57
     onlyOwner
    0.57
     متعلقه
    0.57
     ISNI
    0.55
    setVerticalGroup
    0.55
    TableAdapter
    0.55
    Activations Density 1.391%

    No Known Activations