© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7378
    Prev
    Next
    INDEX
    Explanations

    words and phrases common to academic research papers

    oai_token-act-pair · gemini-2.0-flash

    sample

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    outchouc
    -0.47
    UVWXYZ
    -0.46
     Chore
    -0.45
    zecz
    -0.45
     Wer
    -0.42
     People
    -0.42
    Ľ
    -0.42
    INSTANCE
    -0.41
     Sucher
    -0.41
     Humans
    -0.40
    POSITIVE LOGITS
     sample
    1.15
    sample
    1.00
     samples
    0.92
     Sample
    0.88
     SAMPLE
    0.88
    Sample
    0.82
    SAMPLE
    0.81
     amostra
    0.77
     échanti
    0.76
    новниш
    0.75
    Activations Density 3.920%

    No Known Activations