© 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. 556
    Prev
    Next
    INDEX
    Explanations

    language about societies and political organizations/teams in the context of social issues

    oai_token-act-pair · gemini-2.0-flash

    local communities

    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
     community
    -2.42
    community
    -2.08
    Community
    -1.96
     Community
    -1.88
     COMMUNITY
    -1.84
    COMMUNITY
    -1.70
     comunidad
    -1.40
     comunit
    -1.36
     communauté
    -1.29
     neighborhood
    -1.28
    POSITIVE LOGITS
    licants
    0.59
    getReference
    0.53
    AccessorTable
    0.51
    UnknownFieldSet
    0.49
    ennale
    0.48
    地说道
    0.48
    WindowConstants
    0.47
    //*/
    0.47
     enx
    0.46
     dirilis
    0.45
    Activations Density 4.842%

    No Known Activations