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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13083
    Prev
    Next
    INDEX
    Explanations

    expressions using the word "what", sometimes also picking up personal pronouns and prepositions nearby

    oai_token-act-pair · gemini-2.0-flash

    what

    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
    <bos>
    -1.04
     what
    -0.69
     itſelf
    -0.62
    What
    -0.62
    what
    -0.58
     myſelf
    -0.54
    Litteratur
    -0.53
     himſelf
    -0.51
     poffible
    -0.51
     <=",
    -0.50
    POSITIVE LOGITS
     createSlice
    0.73
    出版年
    0.63
     unknownFields
    0.62
    __(/*!
    0.61
    complexContent
    0.57
    webElementXpaths
    0.56
     NgModule
    0.56
    aard
    0.54
    athread
    0.54
    ruptedException
    0.53
    Activations Density 3.061%

    No Known Activations