© 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. 13616
    Prev
    Next
    INDEX
    Explanations

    words that describe the telling of a story or giving information

    oai_token-act-pair · gemini-2.0-flash

    narrations

    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
    Viitteet
    -0.67
     RVA
    -0.60
     =>'
    -0.54
    juma
    -0.53
    **/
    -0.51
     aDecoder
    -0.51
    ungsbedingungen
    -0.48
    DockStyle
    -0.48
     सत्यापित
    -0.47
    Geplaatst
    -0.46
    POSITIVE LOGITS
    الحياه
    0.69
    GEBURTSDATUM
    0.69
     الرياضيه
    0.57
     whoſe
    0.57
    MemoryWarning
    0.56
     TextEditing
    0.56
     uſe
    0.55
     Needham
    0.55
    ResumeLayout
    0.54
     beginnetje
    0.53
    Activations Density 35.567%

    No Known Activations