© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10792
    Prev
    Next
    INDEX
    Explanations

    phrases that contain a conjunction and some sort of qualification or expression of doubt

    oai_token-act-pair · gemini-2.0-flash

    but

    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
    եկ
    -0.51
     counterfeit
    -0.50
    خصة
    -0.45
    BlockPos
    -0.45
    keyColumn
    -0.44
    DriverManager
    -0.42
     indirectly
    -0.42
    OnClickListener
    -0.42
    WriteHeader
    -0.42
    LocalizedString
    -0.42
    POSITIVE LOGITS
    DockStyle
    0.92
    webElementXpaths
    0.86
     tartalomajánló
    0.78
    دانشنامهٔ
    0.78
     समीक्षक
    0.73
    rungsseite
    0.71
    MemoryWarning
    0.69
    GEBURTSDATUM
    0.65
    twimg
    0.64
    oczes
    0.62
    Activations Density 0.281%

    No Known Activations