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. 7162
    Prev
    Next
    INDEX
    Explanations

    organizations or people that are doing good in the community

    oai_token-act-pair · 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
     Efq
    -0.94
     Shakspeare
    -0.85
     Reſ
    -0.83
     Houſe
    -0.80
     Anſ
    -0.78
     Phry
    -0.77
     againſt
    -0.76
     Conſ
    -0.75
     himſelf
    -0.75
     GenerationType
    -0.75
    POSITIVE LOGITS
     un
    0.64
     original
    0.64
     de
    0.60
     по
    0.58
     y
    0.57
     E
    0.57
     M
    0.56
     il
    0.55
     von
    0.54
    veli
    0.54
    Activations Density 0.209%

    No Known Activations