© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14364
    Prev
    Next
    INDEX
    Explanations

    French words and phrases related to software, such as Ubuntu, Linux, or Windows

    oai_token-act-pair · gemini-2.0-flash

    French language text

    np_max-act · gemini-2.0-flash

    par

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    .
    -0.50
    2
    -0.49
    1
    -0.47
    THE
    -0.47
    3
    -0.46
    6
    -0.46
     The
    -0.43
    4
    -0.42
    0
    -0.42
    my
    -0.41
    POSITIVE LOGITS
     becauſe
    0.96
    SequentialGroup
    0.90
     fhew
    0.89
     "..\..\
    0.89
    
    0.87
     Jefus
    0.84
    osoever
    0.84
    ſelf
    0.84
    athread
    0.84
     Monfieur
    0.82
    Activations Density 0.242%

    No Known Activations