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. 11187
    Prev
    Next
    INDEX
    Explanations

    the word "tree" and related words, sometimes including words or punctuation nearby

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'plant'

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

    tree

    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
    PasswordEncoder
    -0.56
     تضيفلها
    -0.42
    DataSetChanged
    -0.41
    Numerology
    -0.38
    SocketAddress
    -0.38
    lightbox
    -0.38
    riezmann
    -0.37
    coda
    -0.37
     Numerology
    -0.37
    wsdl
    -0.36
    POSITIVE LOGITS
     plants
    1.82
     plant
    1.65
     Plants
    1.55
    Plants
    1.52
     Plant
    1.51
    plants
    1.49
    Plant
    1.47
     vegetation
    1.45
    plant
    1.41
     PLANT
    1.39
    Activations Density 7.490%

    No Known Activations