© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10761
    Prev
    Next
    INDEX
    Explanations

    the word "has" preceded by words like "there" or "had"

    oai_token-act-pair · gemini-2.0-flash

    must

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Portail
    -0.76
    TestingModule
    -0.71
    setContentView
    -0.63
    Xna
    -0.59
    مصادر
    -0.58
    δί
    -0.57
    LEGGI
    -0.56
    IBOutlet
    -0.56
    rungsseite
    -0.55
     SwiftUI
    -0.54
    POSITIVE LOGITS
     gotta
    1.30
     must
    1.08
    must
    1.06
     Gotta
    1.06
     Must
    1.06
    Must
    1.05
    gotta
    1.02
    Gotta
    0.89
     müssen
    0.85
    ต้อง
    0.83
    Activations Density 2.102%

    No Known Activations