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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7121
    Prev
    Next
    INDEX
    Explanations

    locations and political affiliations

    oai_token-act-pair · gemini-2.0-flash

    area

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -1.01
    ↵
    -0.86
    ,
    -0.72
     
    -0.71
      
    -0.69
    .
    -0.66
    "
    -0.65
    '
    -0.65
    <strong>
    -0.64
     (
    -0.63
    POSITIVE LOGITS
     Мексичка
    1.34
    NameInMap
    1.19
    ContentAsync
    1.19
     utafitiHapana
    1.14
    ImageContext
    1.13
    .}~\
    1.11
     ―――――
    1.11
    вгений
    1.09
    ^(@)
    1.09
     NSCoder
    1.09
    Activations Density 1.501%

    No Known Activations