© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 86
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating subjective opinion

    oai_token-act-pair · 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
     rather
    -0.66
     henvisninger
    -0.62
    Datuak
    -0.62
    Rather
    -0.60
    harusnya
    -0.59
    rather
    -0.58
     BoxDecoration
    -0.57
    WebMethod
    -0.56
    شوف
    -0.55
     Rather
    -0.54
    POSITIVE LOGITS
    Vidite
    0.62
    참고
    0.60
    ValueStyle
    0.57
    Diweddarwch
    0.56
     '\\;'
    0.56
    ChildScrollView
    0.56
     متعلقه
    0.55
    出版年
    0.55
    WebAPI
    0.54
    tagHelperRunner
    0.51
    Activations Density 7.587%

    No Known Activations