© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4107
    Prev
    Next
    INDEX
    Explanations

    capital "R" at the beginning of a word, or lower case "r" after a space

    oai_token-act-pair · gemini-2.0-flash

    R

    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
    DispatchToProps
    -0.65
     kaynağından
    -0.64
    XmlAccessType
    -0.64
     députés
    -0.62
    endpush
    -0.61
    InstrumentedTest
    -0.61
    tagHelperRunner
    -0.60
    KommentareTeilen
    -0.60
    principalTable
    -0.58
     <",
    -0.58
    POSITIVE LOGITS
    Personendaten
    0.57
     Soares
    0.54
     firme
    0.51
    ofold
    0.49
     subi
    0.49
    exitRule
    0.46
    ("}\
    0.46
     shrew
    0.45
    nodoc
    0.45
    軋
    0.45
    Activations Density 0.546%

    No Known Activations