© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12276
    Prev
    Next
    INDEX
    Explanations

    a specific measurement format involving numbers and units

    oai_token-act-pair · gemini-2.0-flash

    scientific data

    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
     Audiodateien
    -0.75
    GraphicsUnit
    -0.73
     تانيه
    -0.68
    Демографія
    -0.67
    iligten
    -0.63
    Datuak
    -0.63
    balleur
    -0.62
    UnusedPrivate
    -0.62
    ècie
    -0.61
    twimg
    -0.61
    POSITIVE LOGITS
    ورت
    0.48
    lended
    0.46
    gulan
    0.45
     du
    0.45
     Eingang
    0.44
    WriteBarrier
    0.43
     so
    0.42
     igaz
    0.42
    shadowOpacity
    0.41
     azon
    0.41
    Activations Density 2.696%

    No Known Activations