© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3781
    Prev
    Next
    INDEX
    Explanations

    words and numbers related to automotive engine specifications

    oai_token-act-pair · gemini-2.0-flash

    Vehicle performance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ReusableCell
    -0.87
     للاسماء
    -0.84
     XCTest
    -0.76
    WireFormat
    -0.68
    حياته
    -0.67
    findpost
    -0.66
    aarrggbb
    -0.65
    Tikang
    -0.65
    ंदीखरीदारी
    -0.64
     EconPapers
    -0.63
    POSITIVE LOGITS
     محفوظة
    0.54
     N
    0.38
     n
    0.37
    ň
    0.35
    farwyddwr
    0.35
     касается
    0.35
    částí
    0.34
    SharedDtor
    0.34
     trampa
    0.33
    Leggi
    0.32
    Activations Density 1.968%

    No Known Activations