© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6495
    Prev
    Next
    INDEX
    Explanations

    words related to collective action, governance, and collaboration, as well as identifiers of specific organizations.

    oai_token-act-pair · gemini-2.0-flash

    participation-related concepts

    np_token-act-pair-logits · gpt-4o-mini

    citizen involvement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Parcelize
    -0.59
    Espèce
    -0.46
     polymorph
    -0.46
    Referências
    -0.44
     prefent
    -0.43
     anhyd
    -0.43
    fug
    -0.43
    tawesome
    -0.42
    Šaltiniai
    -0.42
     neceffary
    -0.42
    POSITIVE LOGITS
     participation
    0.69
    TypedDataSet
    0.60
    Voice
    0.60
     Participation
    0.60
    participation
    0.58
     Orrell
    0.58
     nahilalakip
    0.57
     servant
    0.57
     ownership
    0.57
     оригіналу
    0.56
    Activations Density 1.246%

    No Known Activations