© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13423
    Prev
    Next
    INDEX
    Explanations

    sentence fragments in languages other than English including many German and French fragments

    oai_token-act-pair · gemini-2.0-flash

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     na
    -0.67
     tem
    -0.66
     no
    -0.65
     om
    -0.60
     o
    -0.60
     da
    -0.59
     ta
    -0.59
     sin
    -0.58
     ha
    -0.58
     var
    -0.58
    POSITIVE LOGITS
     beginnetje
    0.94
     myſelf
    0.94
     fevere
    0.91
     ſever
    0.85
    StructEnd
    0.84
     Efq
    0.84
     fubject
    0.84
     ARXIV
    0.83
     pleaſure
    0.83
    følgelig
    0.81
    Activations Density 13.655%

    No Known Activations