© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1000
    Prev
    Next
    INDEX
    Explanations

    common conjunctions, prepositions, and adverbs, often in conjunction with the word "the".

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     '\\;'
    -0.88
    Попис
    -0.77
     resourceCulture
    -0.75
    TypedDataSet
    -0.74
     архивлан
    -0.73
     ujednoznacz
    -0.73
     "..\..\..\
    -0.72
     فريبيس
    -0.72
    homonymie
    -0.71
    +#+#
    -0.68
    POSITIVE LOGITS
    ElementException
    0.46
    luğu
    0.45
    aupun
    0.43
     angeb
    0.43
    setopt
    0.42
    GenerationType
    0.42
     AppModule
    0.41
     claimed
    0.40
     Witt
    0.40
    FileWriter
    0.40
    Activations Density 2.964%

    No Known Activations