© 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. 3116
    Prev
    Next
    INDEX
    Explanations

    instances of speaking or believing

    oai_token-act-pair · gemini-2.0-flash

    say

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.73
     Reſ
    -0.69
     greateſt
    -0.66
     uſe
    -0.65
     Conſ
    -0.64
     Diſ
    -0.63
     ſame
    -0.61
     Houſe
    -0.61
     referenties
    -0.60
     Abonnez
    -0.60
    POSITIVE LOGITS
     they
    0.64
     I
    0.64
     we
    0.62
     his
    0.61
     she
    0.59
     he
    0.58
     it
    0.56
     that
    0.54
     this
    0.51
     my
    0.49
    Activations Density 7.598%

    No Known Activations