© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3066
    Prev
    Next
    INDEX
    Explanations

    mathematical equations, CSS snippets and code involving variables

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    rawDesc
    -0.70
    ineno
    -0.52
     typelib
    -0.50
    CopyWith
    -0.48
     even
    -0.48
    entered
    -0.47
    ){\
    -0.47
    ]='\
    -0.46
     entered
    -0.46
    انيف
    -0.46
    POSITIVE LOGITS
     Anſ
    0.67
     Theſe
    0.66
     poffible
    0.59
     itſelf
    0.59
     ſever
    0.59
    wiſe
    0.58
     Respectfully
    0.57
     myſelf
    0.57
     Reſ
    0.57
     Monfieur
    0.56
    Activations Density 31.832%

    No Known Activations