© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10844
    Prev
    Next
    INDEX
    Explanations

    the use of "one" in phrases about time or single items

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "one"

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

    at

    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
     itſelf
    -1.15
     myſelf
    -1.09
     Efq
    -1.06
     raiſ
    -1.04
     whoſe
    -1.03
     pleaſure
    -1.02
     becauſe
    -1.01
     ―――――
    -0.98
     ſtate
    -0.98
     Theſe
    -0.98
    POSITIVE LOGITS
     at
    2.88
     At
    1.69
    At
    1.59
    at
    1.45
     tại
    1.31
     AT
    0.93
     ở
    0.89
     przy
    0.87
     @
    0.81
     	e
    0.81
    Activations Density 4.722%

    No Known Activations