© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14787
    Prev
    Next
    INDEX
    Explanations

    words and phrases that have strong emotional connotations, whether positive or negative.

    oai_token-act-pair · gemini-2.0-flash

    expressing opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyCulture
    -0.76
    AndroidJUnit
    -0.58
     AssemblyProduct
    -0.52
     IService
    -0.51
    PerformLayout
    -0.50
    heets
    -0.48
    Vidite
    -0.47
     AppColors
    -0.47
    WarningLevel
    -0.47
     חיצוניים
    -0.47
    POSITIVE LOGITS
    ']))
    0.65
    ViewFeatures
    0.56
    '])
    0.56
    EndContext
    0.56
     cellpadding
    0.54
    brtc
    0.53
    urut
    0.52
    "])
    0.52
    '],
    0.52
    )])
    0.49
    Activations Density 9.433%

    No Known Activations