© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9937
    Prev
    Next
    INDEX
    Explanations

    words related to technical and economic analysis, including medical and scientific experiments and predicting future trends

    oai_token-act-pair · gemini-2.0-flash

    Anger and resentment

    np_max-act · gemini-2.0-flash

    space-prefixed words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.82
      
    -0.69
    ↵
    -0.64
     I
    -0.61
     S
    -0.60
     A
    -0.60
     C
    -0.60
        
    -0.60
     R
    -0.57
     In
    -0.57
    POSITIVE LOGITS
     auffi
    1.09
     ſch
    0.97
     purpoſe
    0.95
     Diſ
    0.93
     ainfi
    0.93
     AssemblyCulture
    0.93
     greateſt
    0.93
     ſtate
    0.92
     Reſ
    0.92
     Majefty
    0.92
    Activations Density 7.034%

    No Known Activations