© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11618
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear to be emotionally charged opinions

    oai_token-act-pair · gemini-2.0-flash

    don't

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ❋
    -0.47
     NgModule
    -0.46
     Mayr
    -0.45
    eing
    -0.44
    確かに
    -0.44
     pewno
    -0.44
    的確
    -0.43
     democracies
    -0.42
     canoes
    -0.42
    szönöm
    -0.41
    POSITIVE LOGITS
     ویکی‌پدیا
    0.77
    ArrowToggle
    0.75
    UnsafeEnabled
    0.74
     الحره
    0.68
    UrlResolution
    0.67
    #+#
    0.63
    StoryboardSegue
    0.61
    colgroup
    0.59
    Jeografia
    0.57
     saites
    0.56
    Activations Density 1.319%

    No Known Activations