© 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. 10923
    Prev
    Next
    INDEX
    Explanations

    a heterogeneous mix of content, including citations, code fragments, mathematical expressions, and legal jargon

    oai_token-act-pair · 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
     GR
    -1.16
     GD
    -1.05
     GB
    -1.02
     Gr
    -1.01
    GR
    -1.00
     GC
    -0.99
     GH
    -0.98
     GV
    -0.98
     GS
    -0.97
     GP
    -0.97
    POSITIVE LOGITS
    expandindo
    0.82
    UrlResolution
    0.68
    SharedCtor
    0.68
    ApiModelProperty
    0.65
     Numerade
    0.64
    okovic
    0.61
    twimg
    0.60
     EconPapers
    0.60
     NSCoder
    0.60
    #+#
    0.59
    Activations Density 0.519%

    No Known Activations