© 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. 9857
    Prev
    Next
    INDEX
    Explanations

    passages related to students, learning, sustainability, and business practices.

    oai_token-act-pair · gemini-2.0-flash

    work and thinking

    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
    󠁴
    -0.59
     MessageBoxIcon
    -0.56
     فريبيس
    -0.55
     getView
    -0.51
    __':
    -0.51
    AxisAlignment
    -0.50
    numerusform
    -0.50
    migrationBuilder
    -0.50
    enumi
    -0.49
    发表于
    -0.48
    POSITIVE LOGITS
     AssemblyProduct
    0.56
     acredita
    0.54
     end
    0.52
    haca
    0.48
     sincer
    0.47
     Privacidade
    0.47
     Photocase
    0.47
     institution
    0.47
     ivelany
    0.47
    ainville
    0.47
    Activations Density 14.264%

    No Known Activations