© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10398
    Prev
    Next
    INDEX
    Explanations

    prepositions and words commonly found near them.

    oai_token-act-pair · gemini-2.0-flash

    News/blog context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للمعارف
    -1.13
     للاسماء
    -1.03
    expandindo
    -0.98
    complexContent
    -0.97
     sumpay
    -0.96
     nahilalakip
    -0.94
     onOptions
    -0.94
     <=",
    -0.93
     CreateTagHelper
    -0.93
    ContentAsync
    -0.92
    POSITIVE LOGITS
     C
    0.49
     th
    0.47
     the
    0.45
     San
    0.44
     Me
    0.44
     ol
    0.43
     The
    0.43
    ather
    0.43
     thi
    0.42
     Son
    0.42
    Activations Density 5.605%

    No Known Activations