© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6137
    Prev
    Next
    INDEX
    Explanations

    mentions of Malaysia and automotive participation in shows

    oai_token-act-pair · gemini-2.0-flash

    exhibitions/studies

    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
    Personendaten
    -0.99
     ComVisible
    -0.91
    RegistryLite
    -0.88
    MigrationBuilder
    -0.83
    DockStyle
    -0.78
    rungsseite
    -0.75
     NUKAT
    -0.73
    NewUrlParser
    -0.73
    CppMethod
    -0.71
    WriteBarrier
    -0.70
    POSITIVE LOGITS
     exhibition
    0.44
     study
    0.43
     Rho
    0.43
     Property
    0.42
    󠁢
    0.42
    study
    0.41
     Exhibition
    0.41
     feeder
    0.41
    ubin
    0.40
     Study
    0.39
    Activations Density 0.763%

    No Known Activations