© 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. 11536
    Prev
    Next
    INDEX
    Explanations

    mathematical or programmatic expressions with parentheses and numbers

    oai_token-act-pair · gemini-2.0-flash

    opening parentheses and special characters

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

    (

    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
     Efq
    -1.80
     ſche
    -1.73
     myſelf
    -1.72
    ſelf
    -1.70
     greateſt
    -1.67
     purpoſe
    -1.66
     Anſ
    -1.66
     itſelf
    -1.66
     ſtate
    -1.65
     pleaſure
    -1.64
    POSITIVE LOGITS
     
    1.15
     "
    1.01
     P
    0.98
     I
    0.98
     C
    0.97
     A
    0.94
     S
    0.93
     E
    0.92
     B
    0.92
     Y
    0.89
    Activations Density 2.424%

    No Known Activations