© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8271
    Prev
    Next
    INDEX
    Explanations

    the word "zero"

    oai_token-act-pair · gemini-2.0-flash

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.30
    ,
    -1.27
    .
    -1.18
     M
    -1.16
     R
    -1.13
    ↵
    -1.11
    3
    -1.11
    2
    -1.06
     is
    -1.06
     (
    -1.06
    POSITIVE LOGITS
     Efq
    3.19
     myſelf
    3.03
     Monfieur
    2.88
     itſelf
    2.84
     Jefus
    2.81
     purpoſe
    2.77
     ſeveral
    2.73
     Majefty
    2.70
     themſelves
    2.67
     pleaſure
    2.67
    Activations Density 7.347%

    No Known Activations