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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1115
    Prev
    Next
    INDEX
    Explanations

    words and contexts relating to business and art production

    oai_token-act-pair · gemini-2.0-flash

    entertainment content

    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
     pinulongan
    -0.62
     jScrollPane
    -0.59
    Espèce
    -0.58
    rzost
    -0.54
    addPreferredGap
    -0.52
    GraphicsUnit
    -0.52
    رشف
    -0.51
     uska
    -0.51
     Winaray
    -0.51
     незавершена
    -0.50
    POSITIVE LOGITS
     économies
    0.53
    SqlDataReader
    0.52
     religieuses
    0.50
     ordres
    0.48
     kompakt
    0.47
     attentes
    0.47
     gynhyrchwyd
    0.47
     cortas
    0.47
     états
    0.46
     sauvages
    0.46
    Activations Density 21.796%

    No Known Activations