© 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. 7131
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to technology, with a focus on software and web development.

    oai_token-act-pair · gemini-2.0-flash

    appearance

    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
    الحياه
    -0.76
     الحره
    -0.71
     ©️
    -0.68
     CreateTagHelper
    -0.66
     CanadaChoose
    -0.66
    Hauptartikel
    -0.65
    transQ
    -0.64
    AddTagHelper
    -0.64
    SpringBootTest
    -0.60
    .}}
    -0.59
    POSITIVE LOGITS
     looks
    1.88
     Looks
    1.74
     look
    1.74
    Looks
    1.61
    looks
    1.59
     appearance
    1.59
    look
    1.50
     aesthetics
    1.49
     aesthetic
    1.47
     LOOKS
    1.43
    Activations Density 8.396%

    No Known Activations