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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12228
    Prev
    Next
    INDEX
    Explanations

    the word "team" and related terms like "members" or "foundation" in the context of broader collaborative efforts

    oai_token-act-pair · gemini-2.0-flash

    terms related to teams and teamwork

    np_token-act-pair-logits · gpt-4o-mini

    team

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    MessageTagHelper
    -0.63
    katapos
    -0.47
     path
    -0.45
    Group
    -0.41
    enziali
    -0.41
    band
    -0.40
    むしろ
    -0.40
     team
    -0.39
     Group
    -0.39
     поводу
    -0.39
    POSITIVE LOGITS
    StoryboardSegue
    0.82
    TagMode
    0.81
    AndEndTag
    0.77
     CreateTagHelper
    0.70
    HtmlAttribute
    0.65
    GOTREF
    0.65
    IMPORTED
    0.64
     للاسماء
    0.63
     membres
    0.62
    LEGGI
    0.60
    Activations Density 1.727%

    No Known Activations