© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7738
    Prev
    Next
    INDEX
    Explanations

    the word "ease"

    oai_token-act-pair · gemini-2.0-flash

    ease

    np_max-act · gemini-2.0-flash

    ease

    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
     ―――――
    -1.09
     itſelf
    -1.02
     Theſe
    -0.98
     Efq
    -0.95
     Houſe
    -0.93
     AppColors
    -0.92
     ་་
    -0.91
     Monfieur
    -0.91
     doubtnut
    -0.88
     myſelf
    -0.88
    POSITIVE LOGITS
     the
    0.84
    :✨
    0.83
    verwijspagina
    0.83
     an
    0.65
    enterOuterAlt
    0.64
      
    0.64
     a
    0.63
    abestanden
    0.63
     it
    0.60
     its
    0.60
    Activations Density 1.596%

    No Known Activations