© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14750
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "is" followed by a negative

    oai_token-act-pair · gemini-2.0-flash

    not

    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
    balleur
    -0.55
     Jefus
    -0.52
     uVar
    -0.50
     Eſ
    -0.49
     Chriſt
    -0.49
     <=",
    -0.49
    GeoNames
    -0.49
    datagrid
    -0.49
     Inſ
    -0.48
     sessionFactory
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.62
    colgroup
    0.56
     AspNetCore
    0.56
    دانشنامهٔ
    0.56
    InputTagHelper
    0.54
     yet
    0.53
     necessarily
    0.52
    bootstrapcdn
    0.52
     always
    0.50
    QMetaType
    0.50
    Activations Density 1.256%

    No Known Activations