© 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. 2734
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, names, or terms related to online gaming

    oai_token-act-pair · gemini-2.0-flash

    User names from chat logs

    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
     purpoſe
    -0.84
     pleaſure
    -0.78
     himſelf
    -0.77
     ſeveral
    -0.76
     ſtate
    -0.76
     themſelves
    -0.75
     ſche
    -0.75
     itſelf
    -0.74
     myſelf
    -0.73
     fevere
    -0.71
    POSITIVE LOGITS
     <
    0.45
    Go
    0.45
    Ze
    0.44
     Ze
    0.44
     o
    0.44
    Am
    0.43
     Wolf
    0.42
     Go
    0.42
     x
    0.42
     Am
    0.42
    Activations Density 13.367%

    No Known Activations