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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8309
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to personal reflection

    oai_token-act-pair · gemini-2.0-flash

    Events in a narrative

    np_max-act · gemini-2.0-flash
    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
     
    -0.63
    bucha
    -0.57
    ...
    -0.56
    ,
    -0.54
    意思
    -0.54
     fina
    -0.51
     rote
    -0.50
     같
    -0.50
     shovel
    -0.48
    вать
    -0.48
    POSITIVE LOGITS
     ſtate
    1.09
     Efq
    1.07
     enfans
    1.05
     pleaſure
    1.03
     avoient
    1.03
    ſelf
    1.03
     asimismo
    1.01
     myſelf
    0.98
     purpoſe
    0.97
     charité
    0.96
    Activations Density 2.918%

    No Known Activations