© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9006
    Prev
    Next
    INDEX
    Explanations

    articles like "a" and "an" followed by positive adjectives and nouns.

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     myſelf
    -0.88
     himſelf
    -0.87
     تضيفلها
    -0.84
     itſelf
    -0.84
     Efq
    -0.81
     متعلقه
    -0.80
    
    -0.79
    BeginContext
    -0.79
     themſelves
    -0.74
    Personendaten
    -0.74
    POSITIVE LOGITS
     new
    0.57
     false
    0.57
     se
    0.56
     «
    0.55
     ha
    0.55
     di
    0.54
     good
    0.54
     Ha
    0.52
     Se
    0.51
     true
    0.49
    Activations Density 1.638%

    No Known Activations