© 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. 3908
    Prev
    Next
    INDEX
    Explanations

    the word "yes" and also seems to activate on words that can have positive connotations

    oai_token-act-pair · gemini-2.0-flash

    Yes

    np_max-act · gemini-2.0-flash

    Yes Method used: 1 — reason: MAX_ACTIVATING_TOKENS are identical — explanation: Yes

    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
    <bos>
    -0.88
     He
    -0.84
    WebVitals
    -0.82
    SpringBootTest
    -0.75
     betweenstory
    -0.72
     nakalista
    -0.69
    :✨
    -0.69
    原始内容存档于
    -0.69
     referrerpolicy
    -0.67
     EconPapers
    -0.67
    POSITIVE LOGITS
     Monfieur
    1.13
     feroit
    1.03
     étoient
    1.02
     auroit
    1.02
     démocr
    1.01
     enfans
    1.00
     purpoſe
    0.99
     leçons
    0.97
     Theſe
    0.96
     ſmall
    0.95
    Activations Density 2.056%

    No Known Activations