© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15438
    Prev
    Next
    INDEX
    Explanations

    code snippets with some preference for javascript

    oai_token-act-pair · gemini-2.0-flash

    Code syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Monfieur
    -0.98
     doubtnut
    -0.97
    省市镇
    -0.95
     Cæsar
    -0.93
     Houſe
    -0.90
     xenia
    -0.90
     myſelf
    -0.89
     ―――――
    -0.88
     Majefty
    -0.87
     betweenstory
    -0.86
    POSITIVE LOGITS
    )
    1.05
    ),
    1.02
    ");
    0.97
    );
    0.96
    ).
    0.95
    ')
    0.90
    )
    
    0.85
    ")
    0.85
    ');
    0.84
    ):
    0.83
    Activations Density 6.703%

    No Known Activations