© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9744
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions or questions in general followed by punctuation

    oai_token-act-pair · gemini-2.0-flash

    ?

    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
     moschino
    -0.83
     Cæsar
    -0.71
     garda
    -0.69
     Shakspeare
    -0.68
     Mahomet
    -0.68
     Shaksp
    -0.67
     Assyrian
    -0.67
     cdti
    -0.65
     barbarians
    -0.65
     girdle
    -0.65
    POSITIVE LOGITS
     Am
    0.78
     Van
    0.65
     Par
    0.62
     Do
    0.62
     Mar
    0.62
     May
    0.62
     Can
    0.60
     W
    0.60
     My
    0.60
     Back
    0.60
    Activations Density 6.146%

    No Known Activations