© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9977
    Prev
    Next
    INDEX
    Explanations

    words related to projects and/or studies

    oai_token-act-pair · gemini-2.0-flash

    tokens indicating events and roles in studies

    np_token-act-pair-logits · gpt-4o-mini

    scientific studies/events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ConstraintMaker
    -0.90
     ddelweddau
    -0.70
     betweenstory
    -0.69
     nonUne
    -0.68
    "]);
    -0.67
    KURZBESCHREIBUNG
    -0.66
    énario
    -0.62
    jooq
    -0.62
    ']);
    -0.60
    #+#
    -0.60
    POSITIVE LOGITS
    .
    0.59
     Teilnahme
    0.57
     impegno
    0.52
     who
    0.52
    MockMvc
    0.51
     they
    0.48
     <<<<<<<<<<<<<<
    0.48
    AutoScale
    0.46
     graças
    0.44
     grà
    0.43
    Activations Density 9.845%

    No Known Activations