© 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. 11909
    Prev
    Next
    INDEX
    Explanations

    words about catering to someone's personal preferences

    oai_token-act-pair · gemini-2.0-flash

    words related to preferences

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

    preference

    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
     estekak
    -0.91
    AccessorTable
    -0.91
     myſelf
    -0.90
     Reſ
    -0.85
     Мексичка
    -0.85
    AddHtmlAttribute
    -0.84
     itſelf
    -0.83
     photolibrary
    -0.82
     ExecuteAsync
    -0.81
     Theſe
    -0.81
    POSITIVE LOGITS
     preference
    0.90
     preferred
    0.89
     prefer
    0.86
     preferences
    0.86
    preferences
    0.74
     prefers
    0.74
    Preference
    0.73
     interests
    0.72
    preferred
    0.71
    preference
    0.70
    Activations Density 2.296%

    No Known Activations