© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4676
    Prev
    Next
    INDEX
    Explanations

    adjectives and noun phrases, often preceded by articles such as "a" or "an".

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     AssemblyCompany
    -0.65
    ברס
    -0.64
    MigrationBuilder
    -0.63
     مرئيه
    -0.60
    Rüyada
    -0.58
     protoimpl
    -0.57
    webElementXpaths
    -0.57
    Referencies
    -0.56
    QMetaType
    -0.55
    WriteTagHelper
    -0.54
    POSITIVE LOGITS
    )"),
    0.51
     ſay
    0.50
     referenties
    0.48
     hasattr
    0.47
    glą
    0.47
     nouve
    0.47
     primas
    0.47
     Тип
    0.46
     ſtill
    0.46
    },{
    0.46
    Activations Density 1.839%

    No Known Activations