© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7428
    Prev
    Next
    INDEX
    Explanations

    the word "field" followed by other words, sometimes in bold

    oai_token-act-pair · gemini-2.0-flash

    field

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    höhung
    -0.55
     Administrativna
    -0.50
     môi
    -0.49
    pulseira
    -0.47
     termica
    -0.46
     zasady
    -0.46
     Lyndon
    -0.46
    rouvez
    -0.46
     们
    -0.45
    putchar
    -0.45
    POSITIVE LOGITS
     referrerpolicy
    0.75
    sidemargin
    0.63
     strength
    0.61
     protoimpl
    0.59
    httphttps
    0.57
    marshal
    0.57
    strength
    0.56
     متعلقه
    0.56
    허
    0.56
     TRIP
    0.55
    Activations Density 0.686%

    No Known Activations