© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8095
    Prev
    Next
    INDEX
    Explanations

    mentions of potato chips or chocolate chips, and the word sugar.

    oai_token-act-pair · gemini-2.0-flash

    chips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     $\
    -0.98
     $
    -0.90
     the
    -0.86
     [
    -0.85
     a
    -0.84
    ↵
    -0.80
    _
    -0.80
     (
    -0.77
     <
    -0.76
     \
    -0.73
    POSITIVE LOGITS
     myſelf
    1.70
     itſelf
    1.62
     Efq
    1.60
     themſelves
    1.59
     Jefus
    1.58
     poffible
    1.54
     doubtnut
    1.45
     Monfieur
    1.43
     becauſe
    1.41
     pleaſure
    1.39
    Activations Density 3.281%

    No Known Activations