© 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. 15210
    Prev
    Next
    INDEX
    Explanations

    references to images or code found beneath the current text

    oai_token-act-pair · gemini-2.0-flash

    below

    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
     above
    -1.08
     below
    -1.04
    Above
    -0.93
     Above
    -0.91
     Below
    -0.88
    above
    -0.87
    below
    -0.85
     ABOVE
    -0.84
     acima
    -0.82
     BELOW
    -0.79
    POSITIVE LOGITS
     XE
    0.57
    えたら
    0.50
    Soma
    0.50
     Fid
    0.48
     Soma
    0.48
     COB
    0.48
    awtextra
    0.47
    ruptcy
    0.47
    ValueGenerated
    0.47
    ittäin
    0.46
    Activations Density 3.071%

    No Known Activations