© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9406
    Prev
    Next
    INDEX
    Explanations

    code-like segments including brackets and numbers

    oai_token-act-pair · gemini-2.0-flash

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    culada
    -0.51
    endforeach
    -0.49
     Vorsitzende
    -0.47
     contextes
    -0.47
    iks
    -0.47
    setupUi
    -0.47
    mögens
    -0.47
    Étymologie
    -0.46
     interactiva
    -0.46
     Bayard
    -0.46
    POSITIVE LOGITS
    <bos>
    0.90
    __(/*!
    0.55
    enumi
    0.54
    +:+
    0.52
     سكانية
    0.42
     resourceCulture
    0.41
    enumii
    0.41
    PreferredItem
    0.41
    expandindo
    0.40
    modelBuilder
    0.40
    Activations Density 29.242%

    No Known Activations