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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4380
    Prev
    Next
    INDEX
    Explanations

    words from many different European languages, including Spanish, French, Italian, and Portuguese

    oai_token-act-pair · gemini-2.0-flash

    programming language keywords

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

    foreign articles (del/el/au)

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    articolo
    -0.49
    posedge
    -0.49
     comes
    -0.46
     doInBackground
    -0.45
     ocorreu
    -0.44
     فريبيس
    -0.44
     avviene
    -0.43
    pektor
    -0.42
    complexContent
    -0.41
     aconteceu
    -0.41
    POSITIVE LOGITS
     nakalista
    0.78
    UnusedPrivate
    0.65
    WithIOException
    0.63
    endregion
    0.57
    kháu
    0.55
     JSONException
    0.55
     متحده
    0.55
    RegressionTest
    0.54
    ตอน
    0.54
    PerformLayout
    0.53
    Activations Density 0.609%

    No Known Activations