© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9288
    Prev
    Next
    INDEX
    Explanations

    words related to positive feelings or appreciation

    oai_token-act-pair · gemini-2.0-flash

    food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ########.
    -1.14
    #+#
    -0.91
    SequentialGroup
    -0.89
     الحره
    -0.86
     disponibilités
    -0.82
     <<<<<<<<<<<<<<
    -0.81
    RegressionTest
    -0.80
    Personendaten
    -0.78
    :+:
    -0.78
    脚注の使い方
    -0.77
    POSITIVE LOGITS
     food
    0.88
    food
    0.65
     Food
    0.58
     beer
    0.57
    Food
    0.56
     coffee
    0.54
     p
    0.54
     P
    0.53
     good
    0.52
     pizza
    0.52
    Activations Density 1.970%

    No Known Activations