© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4641
    Prev
    Next
    INDEX
    Explanations

    indented lines consisting of numbers or math expressions

    oai_token-act-pair · gemini-2.0-flash

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     
    -0.85
    expandindo
    -0.60
     .
    -0.58
     good
    -0.56
     beautiful
    -0.55
     huge
    -0.54
     #
    -0.52
     amazing
    -0.51
    хьтан
    -0.51
    <eos>
    -0.50
    POSITIVE LOGITS
    __(/*!
    0.79
    帖最后由
    0.69
    WriteLiteral
    0.66
    ISSN
    0.63
    tagHelper
    0.62
    ContentAlignment
    0.61
     zelve
    0.61
    .“
    0.60
     مشين
    0.60
    enumi
    0.59
    Activations Density 7.543%

    No Known Activations