© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5742
    Prev
    Next
    INDEX
    Explanations

    scientific writing including descriptions of methods, theorems and techniques

    oai_token-act-pair · gemini-2.0-flash

    technique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    索
    -0.40
     rang
    -0.39
    afficheront
    -0.37
    績
    -0.37
     mies
    -0.37
     상세
    -0.36
    芥
    -0.36
     Rating
    -0.35
     prome
    -0.35
    umente
    -0.35
    POSITIVE LOGITS
     faſt
    0.86
    ſelf
    0.83
     themſelves
    0.81
     itſelf
    0.81
    AutoresizingMask
    0.80
     ſp
    0.80
     ſche
    0.78
     Monfieur
    0.76
     ſtate
    0.76
     تضيفلها
    0.75
    Activations Density 3.740%

    No Known Activations