© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12972
    Prev
    Next
    INDEX
    Explanations

    words related to chemistry, competitions, or partners

    oai_token-act-pair · gemini-2.0-flash

    mating or the word "mate"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     mate
    -0.79
    mate
    -0.76
    Mate
    -0.71
    mates
    -0.70
     mates
    -0.69
    AutoField
    -0.65
    ngilizce
    -0.59
     quoque
    -0.59
    bud
    -0.59
    RUnlock
    -0.57
    POSITIVE LOGITS
     محفوظة
    0.73
    ChildScrollView
    0.69
    GraphicsUnit
    0.66
    !("{
    0.56
    +'</
    0.53
    كويكب
    0.50
    WithFormat
    0.49
    "),
    0.49
     }}$}
    0.48
    Chham
    0.48
    Activations Density 6.132%

    No Known Activations