© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15529
    Prev
    Next
    INDEX
    Explanations

    plural nouns or nouns ending in 's' describing people or groups of people

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Italijanski
    -0.73
    ✨:
    -0.71
    ãy
    -0.69
     Persians
    -0.69
     Theſe
    -0.68
    extAlignment
    -0.68
    RegistryLite
    -0.66
     moschino
    -0.66
    COUVER
    -0.65
    قایناق‌لار
    -0.65
    POSITIVE LOGITS
     me
    0.51
     him
    0.49
     all
    0.48
     no
    0.47
     either
    0.45
     don
    0.44
     f
    0.43
     I
    0.42
     tested
    0.42
    Skocz
    0.42
    Activations Density 1.534%

    No Known Activations