© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16031
    Prev
    Next
    INDEX
    Explanations

    a variety of possibly related topics, including statistics, politics, github and people's names

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    np_max-act · gemini-2.0-flash
    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
     
    -5.97
    ,
    -5.25
    .
    -5.22
     (
    -5.19
    ↵↵
    -4.91
    ↵
    -4.66
     in
    -4.50
    <eos>
    -4.41
    -
    -4.38
    :
    -4.19
    POSITIVE LOGITS
     myſelf
    10.25
     itſelf
    9.94
     Efq
    9.88
     Monfieur
    9.13
     ―――――
    9.06
     Jefus
    8.88
     Majefty
    8.81
     pleaſure
    8.75
     purpoſe
    8.69
     Theſe
    8.69
    Activations Density 8.991%

    No Known Activations