© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1619
    Prev
    Next
    INDEX
    Explanations

    words related to formal writing, policy or documents

    oai_token-act-pair · gemini-2.0-flash

    official statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     menulis
    -0.71
     écrit
    -0.66
     écrire
    -0.64
     tulisan
    -0.63
     escrito
    -0.60
     écrits
    -0.59
     églises
    -0.58
     tulis
    -0.57
     escrever
    -0.57
     writes
    -0.56
    POSITIVE LOGITS
    IVEREF
    0.60
    Билгалдахарш
    0.60
     interviewed
    0.59
     Interview
    0.58
     Normdatei
    0.57
     interview
    0.57
     jadx
    0.55
    évaluateur
    0.55
     talked
    0.54
     interviewing
    0.54
    Activations Density 22.403%

    No Known Activations