© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10685
    Prev
    Next
    INDEX
    Explanations

    words related to research and scientific reporting often including numbers and citations.

    oai_token-act-pair · gemini-2.0-flash

    Scientific publications

    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
    GEBURTSDATUM
    -1.00
     مرئيه
    -0.89
     '\\;'
    -0.83
    GMENT
    -0.82
    RegressionTest
    -0.82
    brainly
    -0.81
    migrationBuilder
    -0.80
     وتسجيلات
    -0.79
     EconPapers
    -0.78
    AndEndTag
    -0.77
    POSITIVE LOGITS
     
    1.68
    ndre
    0.33
    का
    0.32
    لیل
    0.31
    栄
    0.31
    +")
    0.30
    默
    0.30
     AnyObject
    0.29
    untung
    0.29
    .}
    0.29
    Activations Density 63.113%

    No Known Activations