© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10227
    Prev
    Next
    INDEX
    Explanations

    second person pronouns and related words like you're

    oai_token-act-pair · gemini-2.0-flash

    is or in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    +#+#
    -0.96
     kaarangay
    -0.85
     particular
    -0.76
     ComVisible
    -0.75
    WebVitals
    -0.75
     Signalez
    -0.75
    particular
    -0.75
     nakalista
    -0.74
     PARTICULAR
    -0.73
    帖最后由
    -0.69
    POSITIVE LOGITS
    由
    0.61
    要
    0.57
    以
    0.56
    对
    0.51
    从
    0.49
     Independencia
    0.48
    中国
    0.46
    为了
    0.45
    CreateModel
    0.45
    要做
    0.44
    Activations Density 0.221%

    No Known Activations