© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13671
    Prev
    Next
    INDEX
    Explanations

    mathematical jargon such as "precisely", "that is", and "moreover"

    oai_token-act-pair · gemini-2.0-flash

    technical definitions

    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
    Geplaatst
    -0.86
     defaultstate
    -0.84
    httphttps
    -0.80
    <bos>
    -0.78
    SourceChecksum
    -0.73
    oa̍t
    -0.71
     Phry
    -0.69
     @"/
    -0.68
     nakalista
    -0.68
    DockStyle
    -0.67
    POSITIVE LOGITS
    asikan
    0.51
     neuf
    0.49
     Say
    0.49
     CURIAM
    0.48
    言えば
    0.48
    colate
    0.47
     mes
    0.46
    ('-'
    0.45
    aire
    0.45
     réforme
    0.44
    Activations Density 2.127%

    No Known Activations