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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14746
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and the names/titles of leaders

    oai_token-act-pair · gemini-2.0-flash

    followers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    TagMode
    -0.65
    Демографія
    -0.60
     purpoſe
    -0.55
    lepiej
    -0.54
    хьтан
    -0.52
    ouders
    -0.52
    instancetype
    -0.51
    awtextra
    -0.51
    DockStyle
    -0.51
     Propri
    -0.51
    POSITIVE LOGITS
     disciple
    0.90
     disciples
    0.89
     subordinate
    0.79
     subordinates
    0.77
     assistants
    0.71
     assistant
    0.71
     apprentices
    0.70
     protégé
    0.70
     followers
    0.68
     protege
    0.67
    Activations Density 2.377%

    No Known Activations