© 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. 2306
    Prev
    Next
    INDEX
    Explanations

    negative words or words that signal poor quality

    oai_token-act-pair · gemini-2.0-flash

    low quality, weakness

    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
    ))/(
    -0.65
     متعلقه
    -0.62
    HomeAsUpEnabled
    -0.60
     đương
    -0.59
    NOPQRST
    -0.59
    )}+
    -0.57
    Toponymie
    -0.57
    IBarButtonItem
    -0.56
    Personendaten
    -0.54
    \{\\
    -0.54
    POSITIVE LOGITS
     poor
    0.93
    poor
    0.91
    Poor
    0.86
     POOR
    0.84
     Poor
    0.84
     lack
    0.68
     inadequate
    0.66
     insufficient
    0.64
     poorly
    0.64
     pauvre
    0.62
    Activations Density 1.368%

    No Known Activations