© 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. 10004
    Prev
    Next
    INDEX
    Explanations

    phrases of encouragement like will, benefit, help, and can, often directed at the reader

    oai_token-act-pair · gemini-2.0-flash

    modal verbs

    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
    umpang
    -0.57
    ()?;
    -0.56
     Marked
    -0.54
     Worked
    -0.52
    paigns
    -0.52
    ReadLine
    -0.50
    nextLine
    -0.50
    andExpect
    -0.49
     tensors
    -0.48
    effort
    -0.47
    POSITIVE LOGITS
    UnusedPrivate
    0.65
     مشين
    0.65
     للاسماء
    0.63
    RenderAtEndOf
    0.63
     VIDEOTAPE
    0.62
    出版年
    0.59
     JUGA
    0.56
    AndEndTag
    0.54
     disambiguazione
    0.54
     do
    0.52
    Activations Density 1.909%

    No Known Activations