© 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. 13626
    Prev
    Next
    INDEX
    Explanations

    initials, percentages, numbers, and other quantitative data within reports and documents.

    oai_token-act-pair · gemini-2.0-flash

    Data/code/statistics

    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
    InstanceState
    -0.54
    bewerken
    -0.53
    ioutil
    -0.50
     objectMapper
    -0.47
     Brut
    -0.46
    olen
    -0.45
    seated
    -0.45
    ServletException
    -0.45
    illette
    -0.45
     viewDidLoad
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.71
    MLLoader
    0.61
     aiut
    0.55
    ventajas
    0.54
    νον
    0.54
     defaultstate
    0.54
     autorytatywna
    0.54
    AutoField
    0.54
    #
    0.53
     typelib
    0.52
    Activations Density 10.411%

    No Known Activations