© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15284
    Prev
    Next
    INDEX
    Explanations

    references to a government minister of finance

    oai_token-act-pair · gemini-2.0-flash

    financial terms or roles

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

    Minister

    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
     انداز
    -0.49
     Resolver
    -0.47
     lead
    -0.44
     stra
    -0.43
    บู
    -0.43
     Altern
    -0.42
     multip
    -0.42
     inter
    -0.42
     SCAR
    -0.41
    hopal
    -0.40
    POSITIVE LOGITS
    propTypes
    0.61
    PMailer
    0.57
     propTypes
    0.57
    CPtr
    0.56
     TestBed
    0.55
     وتسجيلات
    0.55
    DoubleQuotes
    0.54
    Portail
    0.54
    Дереккөздер
    0.53
     gyhoeddwyd
    0.53
    Activations Density 0.373%

    No Known Activations