© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11660
    Prev
    Next
    INDEX
    Explanations

    phrases that express difficulty or ease.

    oai_token-act-pair · gemini-2.0-flash

    difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    πως
    -0.47
    дор
    -0.45
     vignette
    -0.44
    なり
    -0.44
     introduction
    -0.44
    vogel
    -0.44
    CurrentValue
    -0.43
    dible
    -0.43
    vignette
    -0.43
    china
    -0.42
    POSITIVE LOGITS
    ResumeLayout
    0.64
     Normdatei
    0.62
    المناصب
    0.61
    ViewFeatures
    0.59
     tasks
    0.56
    easier
    0.56
     tâche
    0.55
     gyhoeddwyd
    0.55
    期刊论文
    0.55
    tasks
    0.54
    Activations Density 1.409%

    No Known Activations