© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15582
    Prev
    Next
    INDEX
    Explanations

    years, especially 4 digit years starting with a 1

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act · gemini-2.0-flash

    1

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AssemblyCulture
    -1.39
     myſelf
    -1.27
    ^(@)
    -1.14
    aarrggbb
    -1.09
    ſelf
    -1.09
     itſelf
    -1.07
     poffible
    -1.06
     ExecuteAsync
    -1.05
     pleaſure
    -1.05
     auffi
    -1.04
    POSITIVE LOGITS
    ↵
    1.13
    ↵↵
    0.84
    </blockquote>
    0.77
    <eos>
    0.76
        
    0.70
    0.68
          
    0.68
    </h4>
    0.68
    0.68
         
    0.67
    Activations Density 2.472%
    No Known Activations