© 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. 10082
    Prev
    Next
    INDEX
    Explanations

    calls to action to read more or find more information

    oai_token-act-pair · gemini-2.0-flash

    end of articles

    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
    TagMode
    -1.00
    tvguidetime
    -0.82
    IndentedString
    -0.81
     Monfieur
    -0.80
    migrationBuilder
    -0.79
    MigrationBuilder
    -0.78
     otomatig
    -0.76
    rungsseite
    -0.76
     Italijanski
    -0.75
     kasarigan
    -0.75
    POSITIVE LOGITS
    ↵
    0.77
    ↵↵
    0.75
    <eos>
    0.65
      
    0.59
     (
    0.59
     -
    0.57
    ,
    0.54
     
    0.50
     Pauly
    0.49
    klärung
    0.48
    Activations Density 7.994%

    No Known Activations