© 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. 5138
    Prev
    Next
    INDEX
    Explanations

    the verb "take" along with prepositions and a, indicating it picks up actions being performed.

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "take"

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

    take

    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
     resourceCulture
    -0.90
    GEBURTSDATUM
    -0.83
    TagMode
    -0.77
     snippetHide
    -0.77
    rrggbb
    -0.75
     pinulongan
    -0.73
    tvguidetime
    -0.69
    WriteTagHelper
    -0.68
    RTLD
    -0.67
     webdriver
    -0.67
    POSITIVE LOGITS
     out
    0.63
     advantage
    0.62
     pity
    0.54
     note
    0.53
     an
    0.53
     a
    0.53
     the
    0.51
     off
    0.50
     wünschen
    0.50
    advantage
    0.49
    Activations Density 2.774%

    No Known Activations