© 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. 6-GEMMASCOPE-TRANSCODER-16K
    4. 15798
    Prev
    Next
    INDEX
    Explanations

    phrases related to acknowledging contributions and citing publications

    oai_token-act-pair · gemini-2.0-flash

    acknowledgements and publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ynchronously
    -0.52
    avigation
    -0.50
     kho
    -0.48
    NullException
    -0.48
    rittura
    -0.46
     ayudarte
    -0.46
    Espèce
    -0.46
    arynx
    -0.45
    googleapis
    -0.45
     tục
    -0.44
    POSITIVE LOGITS
    <bos>
    0.99
    ']))
    
    0.69
    ."));
    0.64
     transfieras
    0.63
    ]})
    0.62
     ")");
    0.60
    protoimpl
    0.60
    endaftaran
    0.60
     */;
    0.59
    ]))
    
    0.59
    Activations Density 3.628%

    No Known Activations