© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14050
    Prev
    Next
    INDEX
    Explanations

    references to a small quantity of items.

    oai_token-act-pair · 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
     couple
    -1.32
    Couple
    -1.19
    couple
    -1.19
     Several
    -1.16
     Couple
    -1.14
    several
    -1.12
     several
    -1.12
    Several
    -1.11
     handful
    -1.07
     alguns
    -0.84
    POSITIVE LOGITS
    BagLayout
    0.75
    bootstrapcdn
    0.75
     '\\;'
    0.67
     للمعارف
    0.66
    Geplaatst
    0.64
    下载附件
    0.62
     EconPapers
    0.62
     muualla
    0.61
    MethodImpl
    0.60
    KURZBESCHREIBUNG
    0.60
    Activations Density 3.953%

    No Known Activations