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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10797
    Prev
    Next
    INDEX
    Explanations

    words related to commerce, locations, governmental entities, and the time of an event

    oai_token-act-pair · gemini-2.0-flash

    openings/launches

    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
     opened
    -2.83
     opening
    -2.77
     open
    -2.75
     Opening
    -2.67
    Opening
    -2.66
     opens
    -2.56
    open
    -2.48
    opening
    -2.45
    Open
    -2.42
     Opened
    -2.41
    POSITIVE LOGITS
    AccessorTable
    0.75
     protoimpl
    0.64
     AssemblyCulture
    0.59
     оригіналу
    0.59
    featureID
    0.58
    MemoryWarning
    0.57
     AttributeSet
    0.55
     pinulongan
    0.54
    #+#
    0.53
     CURIAM
    0.53
    Activations Density 1.810%

    No Known Activations