© 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
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 10303
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by the letters "man", fragments of mathematical equations, news channel names, and process names for doped semiconductor layers.

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    "]];
    -0.67
    SourceChecksum
    -0.65
    ]');
    -0.57
    "]);
    
    -0.56
    })$}
    -0.54
     بای
    -0.53
    '])
    -0.53
    agissait
    -0.51
    '])
    
    -0.50
    "])
    -0.49
    POSITIVE LOGITS
    borderSide
    0.84
    Geplaatst
    0.82
    StandardCharsets
    0.76
    isContained
    0.74
    logrus
    0.72
     ویکی‌پدیا
    0.70
    存于互联网档案馆
    0.70
    клопе
    0.69
    resave
    0.67
    apimachinery
    0.65
    Activations Density 1.150%

    No Known Activations