© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10268
    Prev
    Next
    INDEX
    Explanations

    quantifiers preceding other words, particularly numbers

    oai_token-act-pair · gemini-2.0-flash

    Two/Three

    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
     genoux
    -0.71
     três
    -0.65
     trois
    -0.63
     four
    -0.60
     cinq
    -0.60
     Most
    -0.60
     three
    -0.59
     quatro
    -0.58
     five
    -0.58
     six
    -0.58
    POSITIVE LOGITS
     Efq
    1.34
     Jefus
    1.34
     myſelf
    1.32
     itſelf
    1.26
     Majefty
    1.24
     purpoſe
    1.17
     himſelf
    1.16
     poffible
    1.15
     pleaſure
    1.12
     uſed
    1.11
    Activations Density 8.214%

    No Known Activations