© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13933
    Prev
    Next
    INDEX
    Explanations

    the word "ones".

    oai_token-act-pair · gemini-2.0-flash

    ones

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ones
    -1.00
    RenderAtEndOf
    -0.86
     quelli
    -0.78
    DllImport
    -0.71
    tagext
    -0.69
     coloro
    -0.68
     those
    -0.68
    InjectAttribute
    -0.67
    '));
    -0.67
     notably
    -0.66
    POSITIVE LOGITS
    Somebody
    0.57
    ourdes
    0.55
    unpublished
    0.53
    Източници
    0.53
    ====
    0.52
    nake
    0.52
     Numerade
    0.52
     baka
    0.52
    icles
    0.52
    omenclature
    0.51
    Activations Density 0.974%

    No Known Activations