© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9274
    Prev
    Next
    INDEX
    Explanations

    discourse markers, question words, and elements of reasoning, explanation, or speculation ("how," "if," "so," "reason").

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Is
    -2.27
    Is
    -2.02
     Are
    -1.86
     Has
    -1.74
    Are
    -1.68
    Has
    -1.63
     Was
    -1.62
     Can
    -1.59
     Will
    -1.53
    Can
    -1.48
    POSITIVE LOGITS
     myſelf
    0.90
     greateſt
    0.86
     himſelf
    0.85
    ſelf
    0.83
     Jefus
    0.82
     ſeveral
    0.82
     itſelf
    0.81
     themſelves
    0.81
     Theſe
    0.81
    ſelves
    0.77
    Activations Density 11.332%

    No Known Activations