© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8269
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical data and associated descriptors

    oai_token-act-pair · gemini-2.0-flash

    large numbers and currencies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    OOTDTY
    -0.46
    hopped
    -0.46
    barrow
    -0.43
    guarded
    -0.43
     Chiron
    -0.41
     Inflate
    -0.41
     vectorstock
    -0.40
     oprot
    -0.40
    braith
    -0.38
     CNA
    -0.37
    POSITIVE LOGITS
     nakalista
    0.77
     NUKAT
    0.67
    XmlAccessorType
    0.65
    RenderAtEndOf
    0.64
    \{\\
    0.62
    WaitGroup
    0.60
    NameInMap
    0.60
    CrossRef
    0.59
     beginnetje
    0.59
    圳
    0.57
    Activations Density 23.545%

    No Known Activations