© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 828
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal jargon, website terms, and political language

    oai_token-act-pair · gemini-2.0-flash

    Code and text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     That
    -2.22
    That
    -2.13
     THAT
    -1.89
    THAT
    -1.55
     che
    -1.41
     thats
    -1.31
     dat
    -1.27
     Thats
    -1.19
    that
    -1.18
    Thats
    -1.17
    POSITIVE LOGITS
     Normdatei
    0.77
    حياته
    0.57
     []*
    0.55
     hinaus
    0.54
    <bos>
    0.53
     enx
    0.52
    TextLabel
    0.50
     ویکی‌پدیای
    0.49
     uska
    0.49
    Ligações
    0.48
    Activations Density 9.671%

    No Known Activations