© 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. 11124
    Prev
    Next
    INDEX
    Explanations

    elements that are part of wikitext markup

    oai_token-act-pair · gemini-2.0-flash

    Wiki articles with references

    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
    ↵↵
    -0.90
     The
    -0.77
     A
    -0.76
     I
    -0.75
     It
    -0.75
    <eos>
    -0.73
     m
    -0.72
     We
    -0.71
     C
    -0.71
     X
    -0.70
    POSITIVE LOGITS
     myſelf
    1.09
     ―――――
    1.08
     ་་
    1.03
     pleaſure
    1.03
     Reſ
    1.02
     greateſt
    1.02
     itſelf
    1.00
     raiſ
    0.99
     photolibrary
    0.99
     uſed
    0.97
    Activations Density 1.529%

    No Known Activations