© 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. 14707
    Prev
    Next
    INDEX
    Explanations

    words related to government, institutions, or organizations.

    oai_token-act-pair · gemini-2.0-flash

    describing how things are done

    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
     myſelf
    -1.20
     DBNull
    -1.11
     resourceCulture
    -1.10
    ^(@)
    -1.10
     Efq
    -1.09
     nakalista
    -1.09
    Tembelea
    -1.09
     Wikimedijinoj
    -1.07
    tagHelperRunner
    -1.06
    successfully
    -1.06
    POSITIVE LOGITS
     in
    0.85
     which
    0.74
     to
    0.74
    .
    0.73
     (
    0.73
    ,
    0.71
     on
    0.69
     from
    0.66
     is
    0.65
     with
    0.63
    Activations Density 16.621%

    No Known Activations