© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3782
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to numerical comparisons and reasoning

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Neop
    -0.57
     unknownFields
    -0.55
    #+#
    -0.55
     RULE
    -0.54
     rule
    -0.53
    rophes
    -0.52
     lära
    -0.52
     jspb
    -0.52
     MonoBehaviour
    -0.51
     cref
    -0.51
    POSITIVE LOGITS
     autorytatywna
    0.83
    <bos>
    0.63
     שוליים
    0.60
    ⎨
    0.57
     للمعارف
    0.55
     nahilalakip
    0.53
    Зноскі
    0.53
     average
    0.53
      (
    0.52
     CreateTagHelper
    0.51
    Activations Density 1.508%

    No Known Activations