© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13606
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to official reports and recommendations

    oai_token-act-pair · gemini-2.0-flash

    recommend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.54
    äuser
    -0.45
    ود
    -0.45
    ్రామ
    -0.45
    ks
    -0.44
    孕
    -0.42
     extension
    -0.41
    Género
    -0.41
     h
    -0.41
    REFERENCES
    -0.41
    POSITIVE LOGITS
    ]")]
    0.94
     Italijanski
    0.79
    OGND
    0.78
     GenerationType
    0.73
     contextLoads
    0.72
    UnknownFields
    0.71
     HasFactory
    0.70
    ########.
    0.70
    ngdoc
    0.69
    ="@+
    0.68
    Activations Density 1.434%

    No Known Activations