© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11096
    Prev
    Next
    INDEX
    Explanations

    text that is part of a scientific paper or study

    oai_token-act-pair · gemini-2.0-flash

    ijer

    np_max-act · gemini-2.0-flash

    ijer

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    AndEndTag
    -0.92
     onCreateView
    -0.84
    AddTagHelper
    -0.84
     ویکی‌پدی
    -0.82
    mybatisplus
    -0.75
    AddHtmlAttribute
    -0.73
    évaluateur
    -0.71
     متعلقه
    -0.70
    prepareStatement
    -0.66
    MigrationBuilder
    -0.66
    POSITIVE LOGITS
    LogFactory
    0.67
    ("]");
    0.60
     Semantics
    0.59
    icep
    0.59
     cheek
    0.57
     Maris
    0.55
     Juf
    0.55
    IsContent
    0.54
    toHaveBeenCalled
    0.53
    PIL
    0.53
    Activations Density 5.204%

    No Known Activations