© 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. 13580
    Prev
    Next
    INDEX
    Explanations

    words/phrases indicating direction or movement

    oai_token-act-pair · gemini-2.0-flash

    House locations

    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
    AxisAlignment
    -0.56
     ModelExpression
    -0.53
     AssemblyProduct
    -0.51
     américains
    -0.50
    pendente
    -0.47
     sayap
    -0.47
    HasAnnotation
    -0.47
    外部連結
    -0.46
     BoxFit
    -0.45
    Населення
    -0.45
    POSITIVE LOGITS
    expandindo
    0.65
     tartalomajánló
    0.64
    Tembelea
    0.60
    ]")]
    0.60
     door
    0.57
    ignment
    0.57
     متعلقه
    0.56
     يتيمه
    0.56
    egrave
    0.56
    euse
    0.56
    Activations Density 0.712%

    No Known Activations