© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13200
    Prev
    Next
    INDEX
    Explanations

    mentions of archeology or the history of early civilization.

    oai_token-act-pair · gemini-2.0-flash

    ancient history

    np_max-act · gemini-2.0-flash
    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
     Majefty
    -1.02
     pleaſure
    -0.93
     ſche
    -0.93
     myſelf
    -0.91
     Anſ
    -0.91
     Efq
    -0.90
     leſs
    -0.90
    tvguidetime
    -0.89
     resourceCulture
    -0.89
     fubject
    -0.88
    POSITIVE LOGITS
    quité
    0.64
     zemi
    0.56
    istocene
    0.53
     modern
    0.51
     eeuw
    0.51
     tradizione
    0.51
    [
    0.50
    ↵↵
    0.49
     antichi
    0.48
     Lo
    0.48
    Activations Density 2.730%

    No Known Activations