© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15302
    Prev
    Next
    INDEX
    Explanations

    the word "preference" and related words like "preferable" or "preferring"

    oai_token-act-pair · gemini-2.0-flash

    preference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    2
    -0.85
    1
    -0.82
    4
    -0.80
     Efq
    -0.78
     Cæsar
    -0.76
     Conſ
    -0.76
     Reſ
    -0.74
    ed
    -0.74
    '
    -0.74
     Diſ
    -0.73
    POSITIVE LOGITS
     autorytatywna
    1.32
     propOrder
    1.30
    Personendaten
    1.29
    帖最后由
    1.27
     CWE
    1.26
     unknownFields
    1.24
    Geplaatst
    1.23
    webElementXpaths
    1.20
     Paglinawan
    1.19
    AndEndTag
    1.17
    Activations Density 1.720%

    No Known Activations