© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6749
    Prev
    Next
    INDEX
    Explanations

    words related to either environmental issues/regulations or words related to health in general

    oai_token-act-pair · gemini-2.0-flash

    ecosystems and environmental impacts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ötzlich
    -0.71
    txtName
    -0.62
    eficiente
    -0.59
     HomeComponent
    -0.56
     Exotic
    -0.56
     ALE
    -0.55
     onAnimation
    -0.55
    Portail
    -0.55
    >--}}
    -0.54
     Terrier
    -0.54
    POSITIVE LOGITS
    bitField
    0.53
     OFDb
    0.52
     typelib
    0.52
     ProtoMessage
    0.52
    ंदीखरीदारी
    0.48
    ьаж
    0.48
    ServletException
    0.47
    はじめに
    0.47
    HomeAsUpEnabled
    0.46
    OCCURRED
    0.46
    Activations Density 2.899%

    No Known Activations