© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6542
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs involving people

    oai_token-act-pair · gemini-2.0-flash

    came

    np_max-act · gemini-2.0-flash

    come

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Subview
    -0.57
    DataAnnotations
    -0.55
    äts
    -0.49
    makeText
    -0.47
     intptr
    -0.46
    存于互联网档案馆
    -0.46
    Enllaces
    -0.46
    esub
    -0.45
    protoimpl
    -0.45
     soit
    -0.45
    POSITIVE LOGITS
    <bos>
    1.53
     kteří
    0.76
     who
    0.73
    __':
    0.69
     którzy
    0.63
    躇
    0.63
     Савезне
    0.63
     ktorí
    0.59
    Tikang
    0.58
    プローチ
    0.57
    Activations Density 2.662%

    No Known Activations