© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15598
    Prev
    Next
    INDEX
    Explanations

    the word "demand"

    oai_token-act-pair · gemini-2.0-flash

    demand

    np_max-act · gemini-2.0-flash

    demand Method used: 1 — because every max activating token is the word "demand" — demand

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    expandindo
    -1.08
    AndEndTag
    -1.03
    تقاوى
    -1.02
    بوابة
    -1.00
     Мексичка
    -0.96
    Portale
    -0.96
     nahilalakip
    -0.95
    IUrlHelper
    -0.93
    WebVitals
    -0.90
     otomatig
    -0.90
    POSITIVE LOGITS
    a
    0.66
     individuale
    0.57
    i
    0.53
    :
    0.53
     attack
    0.52
     ons
    0.52
    1
    0.52
    les
    0.51
    й
    0.50
    te
    0.50
    Activations Density 2.755%

    No Known Activations