© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10230
    Prev
    Next
    INDEX
    Explanations

    instances of people changing their minds or something undergoing change

    oai_token-act-pair · gemini-2.0-flash

    change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ValueStyle
    -1.04
    PreferredItem
    -0.65
     resourceCulture
    -0.63
     للاسماء
    -0.61
     CreateTagHelper
    -0.59
    IsMutable
    -0.59
     spesa
    -0.58
     chré
    -0.57
     äta
    -0.57
     فريبيس
    -0.55
    POSITIVE LOGITS
     the
    0.67
    baan
    0.60
     who
    0.59
     variables
    0.58
     count
    0.57
    wikkeld
    0.56
     identities
    0.55
    envs
    0.54
     around
    0.54
     course
    0.54
    Activations Density 5.780%

    No Known Activations