© 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. 3106
    Prev
    Next
    INDEX
    Explanations

    words related to an individual's attitudes and beliefs in a health or educational setting

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
    ronyms
    -0.72
    MarshalTo
    -0.66
     stället
    -0.64
    ocide
    -0.59
     humains
    -0.59
    philis
    -0.57
     prisonniers
    -0.57
     linkovi
    -0.57
    ołnier
    -0.56
    Gön
    -0.54
    POSITIVE LOGITS
    醐
    0.58
    writeFieldEnd
    0.57
    MessageTagHelper
    0.54
     betweenstory
    0.52
     nonatomic
    0.51
     capitals
    0.50
    áso
    0.49
    /***/
    0.49
     fle
    0.49
    GeneratedMessage
    0.47
    Activations Density 1.985%

    No Known Activations