© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13898
    Prev
    Next
    INDEX
    Explanations

    substrings of names or IDs

    oai_token-act-pair · gemini-2.0-flash

    scholarly citations and legal documents

    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
     
    -0.60
    <eos>
    -0.57
     N
    -0.54
    ↵↵
    -0.53
      
    -0.52
     No
    -0.50
    <b>
    -0.50
    .
    -0.48
     (
    -0.48
    ↵
    -0.48
    POSITIVE LOGITS
     myſelf
    1.27
     ―――――
    1.26
     Jefus
    1.23
     Monfieur
    1.22
     Efq
    1.22
     doubtnut
    1.16
     للاسماء
    1.16
     Theſe
    1.14
     itſelf
    1.13
     ――――――――
    1.13
    Activations Density 0.751%

    No Known Activations