© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10106
    Prev
    Next
    INDEX
    Explanations

    Danish text, specifically titles or phrases followed by parenthesized numbers

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages/code

    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
    LookAnd
    -0.59
    arrête
    -0.54
     Suecia
    -0.53
    ällt
    -0.53
     للمعارف
    -0.52
    SpringBootTest
    -0.50
    وأضاف
    -0.49
    richTextPanel
    -0.49
    tissage
    -0.49
     READER
    -0.48
    POSITIVE LOGITS
     []:
    0.66
     nakalista
    0.64
    بوابة
    0.61
     useRouter
    0.56
     den
    0.52
     useStyles
    0.52
    uali
    0.51
    Authentic
    0.50
    AndEndTag
    0.49
    Autoritní
    0.49
    Activations Density 0.358%

    No Known Activations