© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12382
    Prev
    Next
    INDEX
    Explanations

    code related to assertions and invariants

    oai_token-act-pair · gemini-2.0-flash

    assert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     EconPapers
    -0.70
     herewith
    -0.69
    QUADS
    -0.66
    }{*}{}
    -0.62
    itemView
    -0.62
    WillAppear
    -0.62
    urator
    -0.60
     cref
    -0.60
    +#+#
    -0.60
     fibrillation
    -0.59
    POSITIVE LOGITS
    <bos>
    0.91
     Baillargeon
    0.52
    tot
    0.51
    logrus
    0.49
     esteja
    0.43
     tenha
    0.41
    [/
    0.40
    <>();
    0.39
    anmoins
    0.39
     besky
    0.39
    Activations Density 9.013%

    No Known Activations