© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3911
    Prev
    Next
    INDEX
    Explanations

    code blocks that may be related to Java or C# or other curly brace languages, and that use the word "using"

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    .
    -1.06
    <eos>
    -1.02
    ↵↵
    -1.01
    ↵
    -0.98
     (
    -0.98
    ,
    -0.98
     
    -0.91
      
    -0.88
    -
    -0.84
    :
    -0.82
    POSITIVE LOGITS
     myſelf
    1.92
     Efq
    1.91
     itſelf
    1.79
     Monfieur
    1.77
     ―――――
    1.76
    ^(@)
    1.74
     Majefty
    1.74
     purpoſe
    1.72
     $_"
    1.70
     doubtnut
    1.69
    Activations Density 1.734%

    No Known Activations