© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10741
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to community, especially within the context of institutions and values.

    oai_token-act-pair · gemini-2.0-flash

    community

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    InitVars
    -0.53
    Демографія
    -0.47
     mandatario
    -0.47
    ьаж
    -0.47
     Bioaccumulative
    -0.46
     SEDS
    -0.45
    タニ
    -0.45
    argout
    -0.44
    uisine
    -0.44
     Paglinawan
    -0.43
    POSITIVE LOGITS
    usepackage
    0.60
    mazione
    0.56
     of
    0.56
    principalTable
    0.53
     none
    0.53
    toHaveBeenCalled
    0.52
     up
    0.52
     otomatig
    0.52
    tte
    0.51
    abases
    0.51
    Activations Density 15.988%

    No Known Activations