© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11768
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating dislike or negativity

    oai_token-act-pair · gemini-2.0-flash

    like

    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
     néglig
    -0.72
    URLException
    -0.60
    IsContent
    -0.55
    angliski
    -0.54
     chung
    -0.54
    leine
    -0.54
    AutoField
    -0.54
     näm
    -0.52
    ophobic
    -0.52
    FieldBuilder
    -0.52
    POSITIVE LOGITS
    __':
    0.54
    ngdoc
    0.51
    ")));
    0.50
    ConstraintMaker
    0.49
    __":
    0.49
    ыре
    0.48
    ברס
    0.48
    QtGui
    0.47
    )";
    0.46
    SuspendLayout
    0.46
    Activations Density 5.241%

    No Known Activations