© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3553
    Prev
    Next
    INDEX
    Explanations

    seemingly random, but often precedes or includes a single digit number

    oai_token-act-pair · gemini-2.0-flash

    beginning of document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     InputDecoration
    -0.87
    帖最后由
    -0.80
    ंदीखरीदारी
    -0.76
    parsedMessage
    -0.73
     kasarigan
    -0.62
    bootstrapcdn
    -0.62
    jooq
    -0.61
    ArrowToggle
    -0.61
     Theſe
    -0.61
     EconPapers
    -0.59
    POSITIVE LOGITS
    ழு
    0.48
     сна
    0.47
    ⎩
    0.46
    żna
    0.45
    に触
    0.45
    이의
    0.43
    vičius
    0.43
    alade
    0.41
    Hash
    0.41
    StartTag
    0.41
    Activations Density 0.861%

    No Known Activations