© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15736
    Prev
    Next
    INDEX
    Explanations

    a mix of survey-related terminology, especially those related to international or cross-national surveys, and mentions of "German Confederation" and related entities.

    oai_token-act-pair · gemini-2.0-flash

    political unions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ]);
    -0.57
    ])))
    -0.57
     يتيمه
    -0.54
    ]]
    -0.53
    :'/
    -0.50
    évaluateur
    -0.49
    "]));
    -0.49
    >$
    -0.49
     keys
    -0.49
    ']>;
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.90
     življen
    0.55
    ollectionView
    0.55
     FormsModule
    0.53
    MLLoader
    0.50
    Erstellt
    0.50
     Wikimedijinoj
    0.49
    
    0.48
    ########.
    0.48
    yntaxException
    0.47
    Activations Density 0.851%

    No Known Activations