© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14823
    Prev
    Next
    INDEX
    Explanations

    the word "than" and words used in comparison, contrast or decisions

    oai_token-act-pair · gemini-2.0-flash

    rather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     rather
    -1.12
    rather
    -0.94
    Rather
    -0.93
     Rather
    -0.91
     instead
    -0.82
    instead
    -0.72
     plutôt
    -0.66
    Instead
    -0.61
     Instead
    -0.60
    jsonwebtoken
    -0.56
    POSITIVE LOGITS
    endphp
    0.62
     fotografico
    0.60
     pinulongan
    0.57
    ControllerTest
    0.57
     giusti
    0.56
     Thon
    0.56
     specialising
    0.55
     decathlon
    0.54
     chimiques
    0.54
    ichtung
    0.54
    Activations Density 14.117%

    No Known Activations