© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3929
    Prev
    Next
    INDEX
    Explanations

    a wide variety of common words such as "be", "be verb", "it is", "that", "but", "really", "was", "even" and "full".

    oai_token-act-pair · gemini-2.0-flash

    Variations of "full"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    出版年
    -0.96
    tagHelperRunner
    -0.86
    ukone
    -0.78
    AndEndTag
    -0.75
     ExecuteAsync
    -0.71
    GraphicsUnit
    -0.71
    migrationBuilder
    -0.70
     NSCoder
    -0.69
     الاطلاع
    -0.66
    ArrowToggle
    -0.66
    POSITIVE LOGITS
     full
    3.48
    full
    3.22
    Full
    3.11
     Full
    3.05
    FULL
    2.70
     FULL
    2.52
     penuh
    2.05
     pleine
    2.02
     peł
    1.96
     vollen
    1.95
    Activations Density 6.754%

    No Known Activations