© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4112
    Prev
    Next
    INDEX
    Explanations

    words in the context of the X Factor TV show about Simon Cowell paying people to be on TV

    oai_token-act-pair · gemini-2.0-flash

    News and gossip

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     råd
    -0.45
     riuscito
    -0.44
     palvel
    -0.43
     toimi
    -0.42
    еме
    -0.41
     vů
    -0.41
     genoux
    -0.41
     nocturna
    -0.41
     habet
    -0.41
     viewDidLoad
    -0.40
    POSITIVE LOGITS
     Strictly
    0.80
    #+#
    0.70
    Strictly
    0.69
     defaultstate
    0.69
    EndContext
    0.69
    IntoConstraints
    0.68
     Emmer
    0.68
    EDEFAULT
    0.68
    nodoc
    0.66
    Geplaatst
    0.66
    Activations Density 1.576%

    No Known Activations