© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6535
    Prev
    Next
    INDEX
    Explanations

    mentions of courts, historical events, and political analysis.

    oai_token-act-pair · gemini-2.0-flash

    the word 'again' in various forms

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     {}),
    -0.55
    ierre
    -0.54
    omnie
    -0.52
    %</
    -0.51
    asteroide
    -0.48
    '&:
    -0.48
    ">{{$
    -0.47
    ρίες
    -0.47
    ENTES
    -0.46
    '];
    -0.46
    POSITIVE LOGITS
     again
    3.33
    again
    2.97
    Again
    2.91
     Again
    2.88
     AGAIN
    2.47
     novamente
    2.25
     nuevamente
    2.17
     опять
    1.98
    AGAIN
    1.98
     opět
    1.95
    Activations Density 6.895%

    No Known Activations