© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15841
    Prev
    Next
    INDEX
    Explanations

    words related to information, studies, and creation

    oai_token-act-pair · gemini-2.0-flash

    technical and scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Efq
    -0.87
    PreferredItem
    -0.82
     Theſe
    -0.80
     Shakspeare
    -0.77
     Anſ
    -0.74
    AddTagHelper
    -0.74
     Cæsar
    -0.73
    expandindo
    -0.72
    AndEndTag
    -0.71
     InputDecoration
    -0.71
    POSITIVE LOGITS
     bien
    0.64
     od
    0.60
     lot
    0.60
     cu
    0.59
     form
    0.58
     past
    0.57
     ac
    0.55
     насеље
    0.54
     kali
    0.53
     proteins
    0.52
    Activations Density 15.905%

    No Known Activations