© 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. 6687
    Prev
    Next
    INDEX
    Explanations

    question words such as "which" and "what"

    oai_token-act-pair · gemini-2.0-flash

    which

    np_max-act · gemini-2.0-flash

    ▁Which

    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
    ſelf
    -1.44
     Monfieur
    -1.34
     itſelf
    -1.34
     Jefus
    -1.30
     houſe
    -1.30
     raiſ
    -1.27
    bibinfo
    -1.26
    ſelves
    -1.26
     iſt
    -1.25
     pleaſure
    -1.24
    POSITIVE LOGITS
    (
    0.92
    <strong>
    0.88
    S
    0.78
    <em>
    0.77
    1
    0.77
    <i>
    0.74
    b
    0.74
    <u>
    0.74
    B
    0.74
     
    0.73
    Activations Density 1.917%

    No Known Activations