© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14691
    Prev
    Next
    INDEX
    Explanations

    words related to liking or wanting things

    oai_token-act-pair · gemini-2.0-flash

    prefer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     prefer
    -2.27
     preference
    -2.23
     Prefer
    -2.11
    prefer
    -2.03
     preferences
    -1.98
     Preference
    -1.97
     preferred
    -1.96
    Prefer
    -1.96
     prefers
    -1.93
     preferring
    -1.93
    POSITIVE LOGITS
    RectangleBorder
    0.55
     OMITBAD
    0.53
    webElementGuid
    0.53
     lampada
    0.51
    titleMargin
    0.49
     AssemblyCulture
    0.48
     Numerade
    0.48
     Proclamation
    0.47
     aceptas
    0.47
     henvisninger
    0.47
    Activations Density 5.528%

    No Known Activations