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. 14246
    Prev
    Next
    INDEX
    Explanations

    words that relate to abstractions of human endeavor, especially personal fulfillment and social status.

    oai_token-act-pair · gemini-2.0-flash

    Describing someone's qualities/position

    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
    Personensuche
    -1.16
    
    -1.12
    IntoConstraints
    -1.09
    RenderAtEndOf
    -1.09
    الحياه
    -1.02
    VIAF
    -1.01
     OFDb
    -0.99
    __':
    
    -0.98
    ReusableCell
    -0.98
     ModelExpression
    -0.96
    POSITIVE LOGITS
    ,
    0.75
     in
    0.70
     and
    0.69
    .
    0.68
    :
    0.63
    ;
    0.60
     is
    0.53
    '
    0.53
     by
    0.53
    <eos>
    0.52
    Activations Density 6.240%

    No Known Activations