© 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. 9390
    Prev
    Next
    INDEX
    Explanations

    words and phrases that could be part of formal writing such as legal or journalistic works

    oai_token-act-pair · gemini-2.0-flash

    Forms of "be"

    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
    ThroughAttribute
    -0.91
    LookAnd
    -0.57
    !*\
    -0.52
    PreferredItem
    -0.49
    Personendaten
    -0.47
    InstrumentedTest
    -0.44
    клопе
    -0.44
    enschappelijke
    -0.44
    IsContent
    -0.43
     anfangen
    -0.43
    POSITIVE LOGITS
     be
    3.53
    Be
    2.55
    be
    2.53
     Be
    2.50
     BE
    1.93
    BE
    1.64
     soient
    1.62
     sejam
    1.34
     soyez
    1.32
     быть
    1.23
    Activations Density 15.059%

    No Known Activations