© 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. 13790
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliary verbs in the context of personal experiences or parenting advice.

    oai_token-act-pair · gemini-2.0-flash

    Embarrassment

    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
    enumi
    -0.44
    于
    -0.43
    []){
    -0.40
    enumii
    -0.40
     chyb
    -0.39
     AssemblyProduct
    -0.38
     noemen
    -0.36
     tailles
    -0.35
     velkommen
    -0.35
    scaler
    -0.35
    POSITIVE LOGITS
     autorytatywna
    1.18
    ThroughAttribute
    1.00
     crossing
    0.98
     crossed
    0.95
     cross
    0.91
     ModelExpression
    0.91
     crosses
    0.90
    crossing
    0.89
    yntaxException
    0.84
     Cross
    0.83
    Activations Density 2.934%

    No Known Activations