© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12888
    Prev
    Next
    INDEX
    Explanations

    words found in scientific papers, law documents, and religious texts

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    tinya
    -0.56
    Ecotoxicity
    -0.55
    erty
    -0.52
    wohner
    -0.50
    guous
    -0.49
    umers
    -0.49
    мма
    -0.48
    ษา
    -0.47
    assert
    -0.46
    SupportActionBar
    -0.45
    POSITIVE LOGITS
    RectangleBorder
    0.91
    AnimationsModule
    0.66
    kuuta
    0.66
     دیکھیے
    0.62
    istoitu
    0.56
    Portale
    0.56
    RTLD
    0.54
     quæ
    0.54
    DropTable
    0.53
     ongles
    0.53
    Activations Density 4.427%

    No Known Activations