© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6253
    Prev
    Next
    INDEX
    Explanations

    a variety of words and phrases representing different topics, but it has especially strong activation for personal pronouns and words indicating a bad, but possible, situation.

    oai_token-act-pair · gemini-2.0-flash

    negative sentiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    IndentedString
    -0.57
    GEBURTSDATUM
    -0.54
    Personensuche
    -0.52
    }`}
    -0.52
    jsonwebtoken
    -0.51
    GeneratedMessage
    -0.51
    UNRELATED
    -0.49
     вікі
    -0.49
     AssemblyTitle
    -0.49
     belang
    -0.47
    POSITIVE LOGITS
     unpleasant
    1.30
     ugly
    1.00
     disagreeable
    0.96
     uncomfortable
    0.96
     distaste
    0.94
     desagrad
    0.90
     disliked
    0.90
     unattractive
    0.90
     ugli
    0.88
     undesirable
    0.88
    Activations Density 1.624%

    No Known Activations