© 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. 14968
    Prev
    Next
    INDEX
    Explanations

    hedging language and suggestion involving the verb "could".

    oai_token-act-pair · gemini-2.0-flash

    could

    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
     Roskov
    -0.99
    SharedCtor
    -0.71
    AsUp
    -0.71
    kháu
    -0.70
    <bos>
    -0.68
     initComponents
    -0.67
    AccessorTable
    -0.65
    Билгалдахарш
    -0.64
     cherchés
    -0.64
    could
    -0.63
    POSITIVE LOGITS
    Personensuche
    0.48
    Vege
    0.47
    roblast
    0.47
    いかない
    0.47
    appé
    0.46
     culturelle
    0.45
     ?>/
    0.44
    kmäler
    0.43
     uninsured
    0.43
    olarmente
    0.43
    Activations Density 2.822%

    No Known Activations