© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9108
    Prev
    Next
    INDEX
    Explanations

    words that are verbs, often preceeded by "to" or "and" and often with "ed" or "ing" endings.

    oai_token-act-pair · gemini-2.0-flash

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    出版年
    -0.68
    getSystemService
    -0.58
    PropertyChanging
    -0.55
    thme
    -0.54
     ligiloj
    -0.53
     dila
    -0.52
     DbSet
    -0.52
    ActivityCompat
    -0.52
     umur
    -0.51
     ujednoznacz
    -0.51
    POSITIVE LOGITS
     seeks
    0.75
    seeking
    0.71
     seek
    0.71
     seeking
    0.69
     versuchen
    0.68
     Seeking
    0.66
     striving
    0.65
    erdings
    0.65
     Seek
    0.64
    wants
    0.63
    Activations Density 0.777%

    No Known Activations