© 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. 2737
    Prev
    Next
    INDEX
    Explanations

    words used in technical documentation, reports, or analyses.

    oai_token-act-pair · gemini-2.0-flash

    high

    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
     yield
    -2.20
    yield
    -2.16
     Yield
    -2.11
    Yield
    -2.08
     Yields
    -1.94
     yields
    -1.82
     yielding
    -1.72
    yields
    -1.63
     yielded
    -1.55
     harvest
    -1.41
    POSITIVE LOGITS
    ArgumentParser
    0.45
    ConstraintMaker
    0.43
     y
    0.43
     estekak
    0.42
     parab
    0.40
    incen
    0.40
     binders
    0.40
    rinfo
    0.39
    providedIn
    0.39
    KURZBESCHREIBUNG
    0.38
    Activations Density 2.700%

    No Known Activations