© 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. 12604
    Prev
    Next
    INDEX
    Explanations

    words that are related to complex information or government studies and reports

    oai_token-act-pair · gemini-2.0-flash

    "of which" clauses

    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
     which
    -3.53
    which
    -3.03
     WHICH
    -2.70
     Which
    -2.63
    Which
    -2.56
    hich
    -1.87
     которое
    -1.76
     laquelle
    -1.73
     lequel
    -1.70
     które
    -1.69
    POSITIVE LOGITS
    empio
    0.58
    arschijnlijk
    0.53
    VIAF
    0.52
    ignty
    0.52
    THISDAY
    0.48
    archiviato
    0.47
    θεν
    0.46
    kania
    0.46
    μισ
    0.45
    トナム
    0.45
    Activations Density 10.367%

    No Known Activations