© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11427
    Prev
    Next
    INDEX
    Explanations

    instances of comparison using words like "just", "equal", and "not"

    oai_token-act-pair · gemini-2.0-flash

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    -0.47
     crdi
    -0.46
     itſelf
    -0.45
     tuc
    -0.45
     prac
    -0.44
     plural
    -0.44
    neté
    -0.44
     toucher
    -0.44
     '*')
    -0.44
     Multiple
    -0.43
    POSITIVE LOGITS
    SpringBootTest
    0.82
    GraphicsUnit
    0.71
     BoxDecoration
    0.66
    styleUrls
    0.64
    oredCriteria
    0.59
     Walkover
    0.56
    +#+
    0.55
    BeforeEach
    0.54
     елның
    0.54
    colage
    0.54
    Activations Density 3.315%

    No Known Activations