© 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. 6965
    Prev
    Next
    INDEX
    Explanations

    references to organizations and committees

    oai_token-act-pair · gemini-2.0-flash

    associate

    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
    хьтан
    -0.65
     College
    -0.60
     defaultstate
    -0.59
    rrggbb
    -0.59
     college
    -0.57
    DockStyle
    -0.57
     COLLEGE
    -0.56
    College
    -0.56
     '\\;'
    -0.56
    ChildScrollView
    -0.55
    POSITIVE LOGITS
     associate
    0.79
     associates
    0.78
    associate
    0.70
    Associate
    0.70
     Associate
    0.69
     asso
    0.60
     Associates
    0.59
     Peralta
    0.59
     ASSOCI
    0.57
    ASSOCI
    0.56
    Activations Density 0.949%

    No Known Activations