© 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. 14044
    Prev
    Next
    INDEX
    Explanations

    legal and professional job titles and roles, in addition to some seemingly random words

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     ujednoznacz
    -0.71
    ècie
    -0.71
     jsPsych
    -0.71
    ARGV
    -0.70
     digress
    -0.69
     oka
    -0.69
     Blackwell
    -0.68
    okovic
    -0.65
    inesis
    -0.65
     Sono
    -0.65
    POSITIVE LOGITS
     Bentham
    0.69
     CURLOPT
    0.67
    ubin
    0.65
    HttpPut
    0.65
     CRU
    0.61
     Vande
    0.61
     assurent
    0.59
    parentNode
    0.59
     letti
    0.59
     Mati
    0.58
    Activations Density 14.725%

    No Known Activations