© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11382
    Prev
    Next
    INDEX
    Explanations

    passages from the Quran

    oai_token-act-pair · gemini-2.0-flash

    archaic pronouns

    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
    Tikang
    -0.57
    mbals
    -0.55
     BufferedReader
    -0.55
    Upon
    -0.54
    upon
    -0.54
    Dancer
    -0.54
    extAlignment
    -0.53
     Upon
    -0.53
    URLException
    -0.52
     upon
    -0.52
    POSITIVE LOGITS
     pinulongan
    0.73
     Jefus
    0.70
     onely
    0.62
     Houſe
    0.61
     therefrom
    0.61
     thyself
    0.59
     withal
    0.57
     myſelf
    0.57
     <<<<<<<<<<<<<<
    0.57
     themſelves
    0.57
    Activations Density 14.160%

    No Known Activations