© 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. 12583
    Prev
    Next
    INDEX
    Explanations

    sentence fragments consisting of a period followed by whitespace or a comma. It also finds requests in Japanese

    oai_token-act-pair · gemini-2.0-flash

    end punctuation

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

    Code and Japanese text

    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
    Filmografie
    -0.53
    let
    -0.52
     Majefty
    -0.52
     tombé
    -0.52
     reaſon
    -0.49
     packageName
    -0.49
     Jefus
    -0.49
     cauſe
    -0.49
     whoſe
    -0.48
     ſuch
    -0.48
    POSITIVE LOGITS
    出版年
    0.73
     NSCoder
    0.65
     Wicidata
    0.63
    asgi
    0.61
    httphttps
    0.61
    makeConstraints
    0.59
    Personendaten
    0.59
    NTIS
    0.58
    ölker
    0.57
    UnsafeEnabled
    0.57
    Activations Density 0.441%

    No Known Activations