© 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. 790
    Prev
    Next
    INDEX
    Explanations

    the word "to" and pronouns

    oai_token-act-pair · gemini-2.0-flash

    suggestions and instructions

    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
    RUnlock
    -0.66
     оригіналу
    -0.59
    ValueStyle
    -0.57
     وتسجيلات
    -0.56
    GenerationType
    -0.56
     AssemblyCompany
    -0.55
    reathe
    -0.54
     Brows
    -0.54
    scrap
    -0.54
    httphttps
    -0.54
    POSITIVE LOGITS
    nonatomic
    0.61
    Per
    0.52
     utafitiHapana
    0.49
     Per
    0.47
    AFS
    0.47
     täh
    0.45
    Forms
    0.45
     per
    0.44
     DBNull
    0.43
     Dead
    0.42
    Activations Density 10.562%

    No Known Activations