© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9837
    Prev
    Next
    INDEX
    Explanations

    conjunctions, pronouns, and sentence fragments related to technical discussions in multiple languages.

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    fromnode
    -0.81
    bibfield
    -0.76
    ientí
    -0.73
    drawal
    -0.71
    ponym
    -0.70
    expandindo
    -0.69
    bibinfo
    -0.68
    mless
    -0.68
    ilets
    -0.68
    CLUSIVE
    -0.68
    POSITIVE LOGITS
    <bos>
    1.45
    The
    0.57
     The
    0.55
    DockStyle
    0.53
     this
    0.52
    I
    0.51
    this
    0.50
    L
    0.50
    We
    0.49
      
    0.49
    Activations Density 2.014%

    No Known Activations