© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6016
    Prev
    Next
    INDEX
    Explanations

    context related to time and evaluation of a situation

    oai_token-act-pair · gemini-2.0-flash

    uncommon words

    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
     morire
    -0.63
     soldati
    -0.62
     dipendenti
    -0.62
     nôtre
    -0.60
     lavoratori
    -0.60
     mattino
    -0.60
     barbati
    -0.60
     automatiques
    -0.58
     acque
    -0.57
     sauvages
    -0.57
    POSITIVE LOGITS
     autorytatywna
    0.88
    олові
    0.81
    localctx
    0.78
     propOrder
    0.77
    клопе
    0.74
     tournament
    0.71
     intptr
    0.71
     football
    0.68
     exam
    0.65
     footy
    0.65
    Activations Density 3.477%

    No Known Activations