© 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. 1151
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically identifiers and keywords within various programming languages

    oai_token-act-pair · gemini-2.0-flash

    say "="

    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
     :=
    -0.83
     noqa
    -0.75
     <<<<<<<<<<<<<<
    -0.66
     JsonConvert
    -0.65
    WriteBarrier
    -0.64
     nakalista
    -0.63
    ,—
    -0.62
    ineno
    -0.60
    <>("
    -0.59
     =>
    -0.58
    POSITIVE LOGITS
     =
    0.90
     =
    0.61
     الرياضيه
    0.58
     متعلقه
    0.55
    =
    0.54
    expandindo
    0.51
    坞
    0.50
    '];
    0.50
    脚注の使い方
    0.49
    mybatisplus
    0.49
    Activations Density 1.471%

    No Known Activations