© 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. 12670
    Prev
    Next
    INDEX
    Explanations

    sequences of decimal digits

    oai_token-act-pair · gemini-2.0-flash

    large negative numbers

    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
    ModelSerializer
    -0.53
    CppMethod
    -0.48
    TagMode
    -0.47
     كومونز
    -0.47
    eleste
    -0.46
     ifs
    -0.45
     oír
    -0.45
     PSS
    -0.41
     katal
    -0.41
     CLK
    -0.40
    POSITIVE LOGITS
    NOPQRST
    0.75
     lenker
    0.69
    BagLayout
    0.68
    abetes
    0.63
    PhysRevD
    0.60
    zenberg
    0.59
    MigrationBuilder
    0.59
    سمبر
    0.58
     habet
    0.57
     الرياضيه
    0.57
    Activations Density 1.089%

    No Known Activations