© 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. 14205
    Prev
    Next
    INDEX
    Explanations

    the word "hour" and also snippets of text in other languages

    oai_token-act-pair · gemini-2.0-flash

    time

    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
    Negative Logits
     myſelf
    -0.79
     Theſe
    -0.78
     ſche
    -0.78
     leſs
    -0.78
     reft
    -0.77
     ſind
    -0.76
     foon
    -0.76
     Monfieur
    -0.74
     ſeveral
    -0.74
    StoryboardSegue
    -0.72
    POSITIVE LOGITS
     MERCHANTABILITY
    0.57
     the
    0.55
     الاطلاع
    0.54
     was
    0.53
     amidst
    0.52
    AutoScale
    0.52
    اریخ
    0.51
     in
    0.51
     تضيفلها
    0.51
     recaudación
    0.50
    Activations Density 0.222%

    No Known Activations