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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10961
    Prev
    Next
    INDEX
    Explanations

    the word "kind" (often in the phrase "kind of")

    oai_token-act-pair · gemini-2.0-flash

    the word "kind"

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

    kind

    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
     AssemblyTitle
    -0.81
     defaultstate
    -0.79
     BrowserModule
    -0.65
     للاسماء
    -0.65
    LookAnd
    -0.61
     виправивши
    -0.54
    IContainer
    -0.53
    ginous
    -0.52
     समीक्षाओं
    -0.52
    évaluateur
    -0.52
    POSITIVE LOGITS
     Stoppers
    0.57
     nửa
    0.51
    DatabaseError
    0.49
     publicitaires
    0.49
    Istorija
    0.48
    ys
    0.48
    ölker
    0.48
    chen
    0.47
     готов
    0.46
     Feathers
    0.46
    Activations Density 2.459%

    No Known Activations