© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12137
    Prev
    Next
    INDEX
    Explanations

    words indicating something has increased, decreased, or been attempted/refused.

    oai_token-act-pair · gemini-2.0-flash

    again

    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
    Again
    -1.34
     AGAIN
    -1.31
     Again
    -1.27
    again
    -1.20
     nuevamente
    -1.05
     novamente
    -1.03
     опять
    -0.94
     دوباره
    -0.91
     again
    -0.91
     снова
    -0.88
    POSITIVE LOGITS
     ag
    1.04
    Ag
    0.86
     Agn
    0.85
     gain
    0.84
     Ag
    0.83
    gain
    0.79
     Gain
    0.77
     ExecuteAsync
    0.75
     nahilalakip
    0.74
    Datuak
    0.74
    Activations Density 1.058%

    No Known Activations