© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14324
    Prev
    Next
    INDEX
    Explanations

    subjective and emotional language.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Monfieur
    -0.56
     anledning
    -0.55
     beginnetje
    -0.54
    AlterField
    -0.54
     themſelves
    -0.52
     scolaires
    -0.52
     ſtand
    -0.49
     inferiores
    -0.49
     supérieurs
    -0.48
    PerformLayout
    -0.48
    POSITIVE LOGITS
     NgModule
    0.72
     SqlCommand
    0.58
    NgModule
    0.56
     BrowserModule
    0.54
     <=",
    0.51
    òa
    0.51
     sq
    0.51
    ìa
    0.50
    MenuInflater
    0.50
    WebServlet
    0.50
    Activations Density 3.850%

    No Known Activations