© 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. 12258
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases indicating that something is amazing or impressive

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

    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
     Reverso
    -0.59
    RegressionTest
    -0.58
     pulumi
    -0.54
    ValueStyle
    -0.53
    gisi
    -0.50
    èlement
    -0.47
    πομπ
    -0.47
    djangoproject
    -0.47
    bleshooting
    -0.46
     transparan
    -0.46
    POSITIVE LOGITS
     amazing
    0.91
     incredible
    0.87
     spectacular
    0.82
     Amazing
    0.80
     breathtaking
    0.80
     extraordinary
    0.78
     Majefty
    0.78
    amazing
    0.77
     wonderful
    0.77
     awesome
    0.77
    Activations Density 0.381%

    No Known Activations