© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6823
    Prev
    Next
    INDEX
    Explanations

    the word "patient"

    oai_token-act-pair · gemini-2.0-flash

    patient

    np_max-act · gemini-2.0-flash

    patient

    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
     itſelf
    -1.83
     Monfieur
    -1.83
     Theſe
    -1.82
     Anſ
    -1.79
     Diſ
    -1.78
     myſelf
    -1.77
     Majefty
    -1.76
     Reſ
    -1.76
     Houſe
    -1.70
     Efq
    -1.63
    POSITIVE LOGITS
     de
    0.85
     D
    0.84
     L
    0.82
     S
    0.81
     (
    0.81
     V
    0.81
     N
    0.79
     
    0.79
     K
    0.77
     et
    0.77
    Activations Density 1.547%

    No Known Activations