© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6247
    Prev
    Next
    INDEX
    Explanations

    the word "support"

    oai_token-act-pair · gemini-2.0-flash

    support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     support
    -0.87
    ,
    -0.79
     "
    -0.76
    urs
    -0.69
     en
    -0.67
     sub
    -0.65
     contra
    -0.64
     sur
    -0.63
     Fo
    -0.63
    /
    -0.63
    POSITIVE LOGITS
     colorés
    1.41
     fermés
    1.36
     auroit
    1.32
     originaux
    1.31
     vectorielles
    1.31
     feroit
    1.31
     avoient
    1.30
     étoient
    1.30
     rempliss
    1.29
     étoit
    1.28
    Activations Density 1.118%

    No Known Activations