© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10098
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to classification and identification, often but not always in an official or bureaucratic context

    oai_token-act-pair · gemini-2.0-flash

    Discussions and communication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    migrationBuilder
    -0.55
    an
    -0.47
    AlterField
    -0.47
    LookAnd
    -0.47
    oz
    -0.45
    WebServlet
    -0.42
    ervlak
    -0.42
    anj
    -0.41
    тори
    -0.41
     AssemblyTitle
    -0.41
    POSITIVE LOGITS
    i
    1.19
    y
    0.93
    e
    0.84
    s
    0.75
    iation
    0.75
    iK
    0.71
    ił
    0.70
    iM
    0.69
     Wikimedijinoj
    0.68
    iA
    0.68
    Activations Density 2.429%

    No Known Activations