© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11799
    Prev
    Next
    INDEX
    Explanations

    words and phrases with a general association to being important or earnest.

    oai_token-act-pair · gemini-2.0-flash

    serious

    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
     Serious
    -1.12
    Serious
    -1.10
    serious
    -1.05
     serious
    -1.02
     seriousness
    -0.98
     sérieux
    -0.88
     serius
    -0.82
     serio
    -0.76
     sério
    -0.73
     erns
    -0.68
    POSITIVE LOGITS
    EventQueue
    0.47
    évaluateur
    0.47
     linkovi
    0.45
     chạm
    0.45
    הפ
    0.44
     retrô
    0.44
    PDOException
    0.44
    Хьажоргаш
    0.43
     venganza
    0.43
     she
    0.43
    Activations Density 17.723%

    No Known Activations