© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11919
    Prev
    Next
    INDEX
    Explanations

    phrases containing "would like" or "I'd".

    oai_token-act-pair · gemini-2.0-flash

    expressions of preference

    np_token-act-pair-logits · gpt-4o-mini

    would

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     dream
    -0.82
    ^(@)
    -0.79
    astéroïdes
    -0.76
     dreaming
    -0.75
    UserScript
    -0.72
    dream
    -0.71
     itſelf
    -0.67
     tartalomajánló
    -0.67
     XNUMX
    -0.65
    EnableWeb
    -0.65
    POSITIVE LOGITS
     rather
    1.13
     Rather
    1.04
    Rather
    0.98
    rather
    0.91
     liever
    0.81
     like
    0.80
     plutôt
    0.77
     liked
    0.74
     prefer
    0.73
     likes
    0.67
    Activations Density 1.054%

    No Known Activations