© 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. 5286
    Prev
    Next
    INDEX
    Explanations

    expressions of altruism, specifically doing something without expecting reciprocation

    oai_token-act-pair · gemini-2.0-flash

    variations of the verb "receive"

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

    Receiving

    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
     Schwar
    -0.54
    nhung
    -0.52
    urgia
    -0.51
     Negra
    -0.50
    mità
    -0.49
     supremacy
    -0.48
    NoSuchAlgorithm
    -0.47
     хвати
    -0.47
     cucchiai
    -0.47
     Michoacán
    -0.46
    POSITIVE LOGITS
     receives
    0.98
     receive
    0.96
     receiving
    0.90
     Receiving
    0.83
    receive
    0.81
     Receive
    0.81
    receiving
    0.81
    Receiving
    0.81
     received
    0.79
     recieve
    0.78
    Activations Density 1.921%

    No Known Activations