© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5211
    Prev
    Next
    INDEX
    Explanations

    text about teachers, education, and related sentiments.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "teach"

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

    teaching

    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
     дописавши
    -0.68
    ganet
    -0.52
    ixin
    -0.50
    Unmount
    -0.49
     مشين
    -0.49
    gans
    -0.49
    uschen
    -0.49
    tocin
    -0.48
    DataPropertyName
    -0.47
     lavander
    -0.47
    POSITIVE LOGITS
     teaching
    1.73
     teach
    1.66
     Teaching
    1.52
    teaching
    1.49
     Teach
    1.44
    Teaching
    1.42
    teach
    1.41
     TEACHING
    1.41
     TEACH
    1.38
    Teach
    1.36
    Activations Density 1.158%

    No Known Activations