© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13611
    Prev
    Next
    INDEX
    Explanations

    words that could be part of instructions for attaching or detaching something.

    oai_token-act-pair · gemini-2.0-flash

    placing/installing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     дописавши
    -0.81
     وتسجيلات
    -0.80
    BufferException
    -0.67
    MemoryWarning
    -0.65
     pinulongan
    -0.63
     resourceCulture
    -0.60
    ChrTalk
    -0.57
     مرئيه
    -0.57
    twimg
    -0.54
    циони
    -0.54
    POSITIVE LOGITS
    GraphicsUnit
    0.53
    bkz
    0.52
    المكان
    0.50
    Coach
    0.49
     polaire
    0.48
     Coach
    0.47
    出版年
    0.47
     Pelop
    0.46
     expériment
    0.45
     DPRD
    0.44
    Activations Density 3.616%

    No Known Activations