© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9454
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns combined with prepositions or words like “jail”, “die”, or “neck”

    oai_token-act-pair · gemini-2.0-flash

    reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    providedIn
    -0.76
    
    -0.63
     itself
    -0.63
     للاسماء
    -0.60
     자신의
    -0.58
     sich
    -0.58
    Kaieteur
    -0.58
     Мексичка
    -0.57
     своё
    -0.57
     themselves
    -0.57
    POSITIVE LOGITS
     cauſe
    0.58
     pleaſure
    0.55
     estekak
    0.54
    ValueGenerated
    0.53
     ſhall
    0.51
     theſe
    0.50
    ControllerTest
    0.50
     Reſ
    0.50
     auffi
    0.49
     greateſt
    0.48
    Activations Density 2.635%

    No Known Activations