© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12654
    Prev
    Next
    INDEX
    Explanations

    language related to measuring and understanding climate change

    oai_token-act-pair · gemini-2.0-flash

    climate change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    WindowConstants
    -0.68
     handleMessage
    -0.67
    GraphicsUnit
    -0.66
    BASEPATH
    -0.66
    IntoConstraints
    -0.63
     CreateTagHelper
    -0.63
    artifactId
    -0.63
    DotNetBar
    -0.57
    BeginContext
    -0.55
    uldig
    -0.54
    POSITIVE LOGITS
     preſent
    0.58
    ContentAsync
    0.58
     themſelves
    0.57
     argint
    0.56
    unehmen
    0.55
     Daß
    0.54
     purpoſe
    0.53
     pleaſure
    0.53
     uſe
    0.53
     greateſt
    0.53
    Activations Density 0.360%

    No Known Activations