© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12264
    Prev
    Next
    INDEX
    Explanations

    words associated with communication, food, and parental influence

    oai_token-act-pair · gemini-2.0-flash

    texting or ordering food

    np_max-act · gemini-2.0-flash

    ordering/eating/shopping actions

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Ỉ
    -0.58
    VersionUID
    -0.57
     leth
    -0.53
    enciaga
    -0.53
    rovnik
    -0.51
     Ass
    -0.50
    quelles
    -0.50
     milieux
    -0.49
     isothermal
    -0.49
     especiais
    -0.49
    POSITIVE LOGITS
    <bos>
    1.33
     eat
    0.80
     мәкал
    0.72
     eating
    0.68
     eats
    0.65
     ate
    0.62
     Eat
    0.58
    Eat
    0.58
    rungsseite
    0.57
     speak
    0.56
    Activations Density 1.376%

    No Known Activations