© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11367
    Prev
    Next
    INDEX
    Explanations

    discourse on some really bad historical event, or potentially racist sentiment

    oai_token-act-pair · gemini-2.0-flash

    specific terms or technical jargon

    np_token-act-pair-logits · gpt-4o-mini

    Disasters and large events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Sharpe
    -0.46
     AssemblyCompany
    -0.45
    stone
    -0.45
     cycl
    -0.44
     ivelany
    -0.44
    htbp
    -0.42
    NewGuid
    -0.42
    throm
    -0.41
     góc
    -0.41
     harness
    -0.41
    POSITIVE LOGITS
    WireFormatLite
    0.66
     оригіналу
    0.63
     cherchés
    0.63
     disambiguazione
    0.62
    Rhestr
    0.62
    tvguidetime
    0.56
    kmäler
    0.55
    InstrumentedTest
    0.55
    ActivityCompat
    0.54
     laiton
    0.54
    Activations Density 0.954%

    No Known Activations