© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9890
    Prev
    Next
    INDEX
    Explanations

    mathematical or diagrammatical notation and also words associated with sexual activity

    oai_token-act-pair · gemini-2.0-flash

    incoherent text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     splashes
    -0.81
     cracks
    -0.79
     Shuffle
    -0.79
     Splash
    -0.79
     Bounce
    -0.78
     Squeeze
    -0.78
    Crawl
    -0.77
     Stroll
    -0.77
     swings
    -0.76
    Slap
    -0.75
    POSITIVE LOGITS
    انجليز
    0.59
    Specifications
    0.56
    ophylla
    0.55
    Hotels
    0.54
     Offices
    0.54
     egens
    0.54
    fassungs
    0.53
    redning
    0.53
     steder
    0.52
    Antibodies
    0.51
    Activations Density 3.781%

    No Known Activations