© 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. 10706
    Prev
    Next
    INDEX
    Explanations

    code snippets, primers and parameters

    oai_token-act-pair · gemini-2.0-flash

    code and parameters

    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
    ri
    -0.50
     
    -0.48
     باسم
    -0.47
    #
    -0.47
    en
    -0.45
     #
    -0.45
      
    -0.45
    Search
    -0.44
     called
    -0.43
    P
    -0.43
    POSITIVE LOGITS
    parsedMessage
    1.01
    IsContent
    1.01
     DBNull
    0.89
    PyExc
    0.87
    contentLoaded
    0.86
    PMailer
    0.83
     متعلقه
    0.83
    ⓧ
    0.82
    httphttps
    0.82
    évaluateur
    0.81
    Activations Density 4.744%

    No Known Activations