© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13631
    Prev
    Next
    INDEX
    Explanations

    contractions, especially those ending in "'d", and personal pronouns.

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     voldoende
    -0.46
    miştir
    -0.45
    usercontent
    -0.43
     correta
    -0.40
    /*
    -0.40
     stazione
    -0.39
    Polecam
    -0.39
     mdf
    -0.39
     Sosa
    -0.39
     inhoud
    -0.39
    POSITIVE LOGITS
    IUrlHelper
    0.86
     nahilalakip
    0.84
     חיצוניים
    0.82
    ftagPool
    0.77
    expandindo
    0.77
    awtextra
    0.75
     InputDecoration
    0.73
     autorytatywna
    0.72
     الدولى
    0.68
    الدراسه
    0.67
    Activations Density 1.218%

    No Known Activations