© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8781
    Prev
    Next
    INDEX
    Explanations

    words related to teaching English to foreign language learners

    oai_token-act-pair · gemini-2.0-flash

    terms related to language learning

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

    language learning

    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
    /**
    -0.57
    /*
    -0.55
    Armed
    -0.49
     bowled
    -0.49
    encode
    -0.47
    lussen
    -0.46
    bonucleic
    -0.46
    beros
    -0.46
    anderen
    -0.46
     Paglinawan
    -0.45
    POSITIVE LOGITS
     listening
    0.81
    listening
    0.75
     native
    0.71
     Listening
    0.70
     speaking
    0.65
    native
    0.65
    Listening
    0.64
     dialogues
    0.64
    ValueStyle
    0.63
     conversation
    0.60
    Activations Density 1.105%

    No Known Activations