© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10136
    Prev
    Next
    INDEX
    Explanations

    text describing the importance of research related to combined inverters

    oai_token-act-pair · gemini-2.0-flash

    Importance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     recevrez
    -0.63
    ConverterFactory
    -0.57
     poches
    -0.56
    MemoryWarning
    -0.56
    IMHO
    -0.52
     tromper
    -0.52
     hadapan
    -0.52
     miliki
    -0.50
     MediatR
    -0.49
     dilaporkan
    -0.49
    POSITIVE LOGITS
     समीक्षक
    0.65
    awtextra
    0.60
    ouver
    0.56
    MigrationBuilder
    0.54
     πισ
    0.52
     Sols
    0.52
    Uninitialized
    0.50
     sult
    0.49
     manik
    0.49
    PropertyChanging
    0.48
    Activations Density 3.326%

    No Known Activations