© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5692
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with excess or overindulgence

    oai_token-act-pair · gemini-2.0-flash

    words related to dietary effects or foods

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

    Food and cooking

    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
     AssemblyCulture
    -0.92
    
    -0.83
     MainAxisSize
    -0.83
    \{\\
    -0.80
     initComponents
    -0.79
    клопе
    -0.75
    Vidite
    -0.74
     للاسماء
    -0.73
    Reklama
    -0.71
    $_['
    -0.71
    POSITIVE LOGITS
    wer
    0.41
    saraba
    0.41
    ang
    0.40
     Fo
    0.39
     effect
    0.37
     soup
    0.36
     raw
    0.36
    effect
    0.36
     Q
    0.35
     meat
    0.35
    Activations Density 0.685%

    No Known Activations