© 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. 13064
    Prev
    Next
    INDEX
    Explanations

    the articles "a" and potentially "the" following certain prepositions or adjacent to words with a "t" sound.

    oai_token-act-pair · gemini-2.0-flash

    long

    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
    WriteBarrier
    -0.67
     FetchType
    -0.66
    GeneratedCode
    -0.64
    Portale
    -0.60
    astify
    -0.59
    jspx
    -0.59
     <=",
    -0.59
    contentLoaded
    -0.59
    nodoc
    -0.57
     فريبيس
    -0.57
    POSITIVE LOGITS
     long
    2.11
    long
    1.72
    Long
    1.43
     Long
    1.38
     LONG
    1.30
    LONG
    1.19
     lungo
    1.05
     longa
    1.00
     longterm
    0.93
     longo
    0.91
    Activations Density 4.155%

    No Known Activations