Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13238
    Prev
    Next
    INDEX
    Explanations

    the word "give" or a close variation of it.

    oai_token-act-pair · gemini-2.0-flash

    give

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     give
    -1.85
     giving
    -1.70
    give
    -1.69
    Give
    -1.69
     Give
    -1.61
    Giving
    -1.59
     GIVE
    -1.51
     Giving
    -1.49
     gives
    -1.47
     gave
    -1.46
    POSITIVE LOGITS
    ghu
    0.55
    ::_('
    0.50
    PhysRev
    0.49
    出版年
    0.47
    waz
    0.47
    antMatchers
    0.47
    ieteur
    0.46
     CURLOPT
    0.46
     Fo
    0.45
     wrongs
    0.45
    Activations Density 2.878%

    No Known Activations