© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6529
    Prev
    Next
    INDEX
    Explanations

    intensifiers that boost the impact of what is being described.

    oai_token-act-pair · gemini-2.0-flash

    intensifiers

    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
     فريبيس
    -0.79
     المعيارى
    -0.76
    цездатний
    -0.71
     virkelig
    -0.70
     verkligen
    -0.69
     veramente
    -0.68
     виправивши
    -0.67
     utafitiHapana
    -0.65
     realy
    -0.65
     davvero
    -0.63
    POSITIVE LOGITS
    prehensive
    0.54
    successful
    0.51
     easy
    0.50
     profitable
    0.50
     lucrative
    0.49
     contentious
    0.48
     controversial
    0.48
     multi
    0.48
     successful
    0.48
    PDOException
    0.48
    Activations Density 1.480%

    No Known Activations