© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6158
    Prev
    Next
    INDEX
    Explanations

    code snippets containing while loops or conditionals in a variety of programming languages

    oai_token-act-pair · gemini-2.0-flash

    while

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    -0.56
    Demografie
    -0.55
    MigrationBuilder
    -0.47
     OFDb
    -0.45
    Espèce
    -0.45
    Népesség
    -0.43
     XCTest
    -0.43
    UpInside
    -0.42
    lio
    -0.41
    łecz
    -0.40
    POSITIVE LOGITS
    sizeCache
    0.66
    InstrumentedTest
    0.64
    ValueStyle
    0.61
    ExtendWith
    0.59
    AutoScaleMode
    0.58
    VIAF
    0.58
    Autoritní
    0.57
    contentLoaded
    0.57
    ProcessEvent
    0.56
    crypted
    0.55
    Activations Density 0.621%

    No Known Activations